Skills/Claude Code plugins/salesforce-development

salesforce-development@2.5.0

CAUTION

Publisher claims: "Build Salesforce apps and agents using these core building blocks: metadata, Apex, deploy/retrieve, security, reporting, and generated installed-versus-available capability discovery." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry Claude Code plugin marketplacePublisher forcedotcom · joined 0 days agoInstalls 0Last detonated 1 h ago
What would fix thisWatchDispute verdict

Is [email protected] safe to install?

KillerSkills ran it in the KillerSkills honeypot sandbox (1 scenario) on 2026-10-27 and scored it 68/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Rule modification attempt; Rule modification attempt; Persistence: instructs the agent to auto-load this skill in future sessions. Summary: no network, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 0 s · 1 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
0.0sprocessscript backend runs setup only
0.0sprocessscript backend runs setup only

Static findings

CRITICAL
Rule modification attemptskills/platform-custom-report-type-generate/SKILL.md:71 · Rule modification attempt — overwriting existing instructionsFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
Python subprocess execution detectedscripts/codex_startup.py:20 · Python subprocess execution detectedFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
File type combined with upload actionbin/sf-lsp-host.bundled.js:15 · File type combined with upload action — agent may exfiltrate local data filesFix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
Process kill commandbin/lsp-doctor.bundled.js:1 · Process kill command — agent can terminate processesFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
CRITICAL
Rule modification attemptskills/platform-list-view-generate/SKILL.md:108 · Rule modification attempt — overwriting existing instructionsFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
Process kill commandscripts/test/README.md:146 · Process kill command — agent can terminate processesFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Persistence: instructs the agent to auto-load this skill in future sessionsskills/platform-metadata-retrieve/SKILL.md:3 · Persistence: instructs the agent to auto-load this skill in future sessionsFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
CRITICAL
Rule modification attemptskills/platform-report-generate/SKILL.md:75 · Rule modification attempt — overwriting existing instructionsFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
HIGH
Persistence: instructs the agent to auto-load this skill in future sessionsskills/platform-custom-tab-generate/SKILL.md:3 · Persistence: instructs the agent to auto-load this skill in future sessionsFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
File type combined with upload actionskills/dx-org-manage/SKILL.md:108 · File type combined with upload action — agent may exfiltrate local data filesFix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
CRITICAL
Rule modification attemptskills/platform-report-generate/SKILL.md:29 · Rule modification attempt — overwriting existing instructionsFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
CRITICAL
Rule modification attemptskills/platform-custom-report-type-generate/SKILL.md:59 · Rule modification attempt — overwriting existing instructionsFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
Python subprocess execution detectedscripts/sf_telemetry.py:2554 · Python subprocess execution detectedFix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST05
MEDIUM
Python subprocess execution detectedscripts/feature_detection.py:151 · Python subprocess execution detectedFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
CRITICAL
Rule modification attemptskills/platform-report-generate/SKILL.md:56 · Rule modification attempt — overwriting existing instructionsFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
File type combined with upload actionskills/dx-org-manage/SKILL.md:114 · File type combined with upload action — agent may exfiltrate local data filesFix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
CRITICAL
Rule modification attemptskills/platform-list-view-generate/SKILL.md:85 · Rule modification attempt — overwriting existing instructionsFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
File type combined with upload actionskills/dx-org-manage/SKILL.md:132 · File type combined with upload action — agent may exfiltrate local data filesFix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
File type combined with upload actionskills/dx-org-manage/SKILL.md:23 · File type combined with upload action — agent may exfiltrate local data filesFix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
CRITICAL
Rule modification attemptskills/platform-report-generate/SKILL.md:42 · Rule modification attempt — overwriting existing instructionsFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
File permission modification commandscripts/sf_telemetry.py:177 · File permission modification command — agent changes file ownership/permissionsFix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST05
MEDIUM
File type combined with upload actionbin/sf-lsp-host.bundled.js:30 · File type combined with upload action — agent may exfiltrate local data filesFix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
Python subprocess execution detectedscripts/sf_telemetry.py:1218 · Python subprocess execution detectedFix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST05
MEDIUM
File type combined with upload actionbin/sf-lsp-host.bundled.js:7 · File type combined with upload action — agent may exfiltrate local data filesFix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
HIGH
Persistence: instructs the agent to auto-load this skill in future sessionsskills/platform-validation-rule-generate/SKILL.md:3 · Persistence: instructs the agent to auto-load this skill in future sessionsFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
CRITICAL
Rule modification attemptskills/platform-list-view-generate/SKILL.md:76 · Rule modification attempt — overwriting existing instructionsFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
npx invocation of non-well-known packagescripts/sf_shim.py:392 · npx invocation of non-well-known package — may execute untrusted codeFix: Pin versions and sources; vendor anything fetched at install time.
AST06
CRITICAL
Rule modification attemptskills/platform-list-view-generate/SKILL.md:119 · Rule modification attempt — overwriting existing instructionsFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
CRITICAL
Rule modification attemptskills/platform-custom-report-type-generate/SKILL.md:82 · Rule modification attempt — overwriting existing instructionsFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
File permission modification commandscripts/sf_telemetry.py:218 · File permission modification command — agent changes file ownership/permissionsFix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST05
MEDIUM
File type combined with upload actionbin/sf-lsp-host.bundled.js:13 · File type combined with upload action — agent may exfiltrate local data filesFix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
HIGH
Coercive compliance languageskills/automation-flow-generate/SKILL.md:36 · Coercive compliance languageFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
CRITICAL
Rule modification attemptskills/platform-report-generate/SKILL.md:38 · Rule modification attempt — overwriting existing instructionsFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
CRITICAL
Rule modification attemptskills/platform-custom-report-type-generate/SKILL.md:100 · Rule modification attempt — overwriting existing instructionsFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
CRITICAL
Rule modification attemptskills/platform-list-view-generate/SKILL.md:130 · Rule modification attempt — overwriting existing instructionsFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
Python subprocess execution detectedscripts/sf_telemetry.py:2528 · Python subprocess execution detectedFix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST05
CRITICAL
Rule modification attemptskills/platform-custom-report-type-generate/SKILL.md:90 · Rule modification attempt — overwriting existing instructionsFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
File type combined with upload actionskills/platform-metadata-retrieve/SKILL.md:93 · File type combined with upload action — agent may exfiltrate local data filesFix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
Process kill commandskills/platform-custom-setting-generate/SKILL.md:3 · Process kill command — agent can terminate processesFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
File type combined with upload actionskills/platform-metadata-retrieve/SKILL.md:105 · File type combined with upload action — agent may exfiltrate local data filesFix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
File type combined with upload actionskills/platform-custom-object-generate/SKILL.md:28 · File type combined with upload action — agent may exfiltrate local data filesFix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
Process kill commandskills/platform-custom-setting-generate/SKILL.md:30 · Process kill command — agent can terminate processesFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandskills/platform-lsp-integrate/SKILL.md:191 · Process kill command — agent can terminate processesFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
File type combined with upload actionskills/platform-manifest-generate/SKILL.md:122 · File type combined with upload action — agent may exfiltrate local data filesFix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
Process kill commandskills/platform-lsp-integrate/SKILL.md:52 · Process kill command — agent can terminate processesFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
File type combined with upload actionskills/platform-destructive-deploy/SKILL.md:39 · File type combined with upload action — agent may exfiltrate local data filesFix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
File type combined with upload actionskills/platform-manifest-generate/SKILL.md:34 · File type combined with upload action — agent may exfiltrate local data filesFix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
Process kill commandskills/platform-lsp-integrate/SKILL.md:151 · Process kill command — agent can terminate processesFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
File type combined with upload actionskills/platform-manifest-generate/SKILL.md:159 · File type combined with upload action — agent may exfiltrate local data filesFix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
LOW
Unpinned dependencyskills/platform-environment-validate/SKILL.md:192 · Unpinned dependencyFix: Pin the exact version (`[email protected]`, `==1.2.3`) so every install gets the bytes that were reviewed.
AST06
MEDIUM
File type combined with upload actionskills/platform-manifest-generate/SKILL.md:3 · File type combined with upload action — agent may exfiltrate local data filesFix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
File type combined with upload actionskills/dx-org-manage/SKILL.md:243 · File type combined with upload action — agent may exfiltrate local data filesFix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
LOW
Unpinned dependencyskills/platform-environment-validate/SKILL.md:162 · Unpinned dependencyFix: Pin the exact version (`[email protected]`, `==1.2.3`) so every install gets the bytes that were reviewed.
AST06

What would make this Verified

12 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Unclaimed publisher≈ +8 on the totalClaim forcedotcom: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  2. Unpinned dependencies≈ +3 on the totalPin exact versions (and ideally hashes) in package.json, requirements or the install script so the bundle cannot change under you.
  3. Python subprocess execution detected≈ +2 on the totalBuild commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
  4. File type combined with upload action≈ +2 on the totalRemove the call, or declare the host in frontmatter and explain in the README what is sent and why.
  5. Process kill command≈ +2 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
  6. File permission modification command≈ +2 on the totalRemove the call, or declare the host in frontmatter and explain in the README what is sent and why.
Publish a new version to Claude Code plugins, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim forcedotcom