Skills/Claude Code plugins/agentforce-adlc

agentforce-adlc@0.12.0

CAUTION

Publisher claims: "Agentforce Agent Development Life Cycle — author, discover, scaffold, deploy, test, and optimize .agent files" Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry Claude Code plugin marketplacePublisher salesforceairesearch · joined 0 days agoInstalls 0Last detonated 56 min ago

Dispute verdict

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

Static findings

CRITICAL

Context shift attemptREADME.md:245 · Context shift attempt — trying to change operational mode

AST01

CRITICAL

Pipe-to-shell patternREADME.md:78 · Pipe-to-shell pattern — downloads and immediately executes remote code

AST06

CRITICAL

Pipe-to-shell patternREADME.md:280 · Pipe-to-shell pattern — downloads and immediately executes remote code

AST06

CRITICAL

Prompt injectionREADME.md:245 · Prompt injection — known jailbreak technique reference

AST01

CRITICAL

System prompt continuationskills/agentforce-generate/references/examples.md:74 · System prompt continuation — attempts to append to system instructions

AST01

CRITICAL

Privileged sudo commandREADME.md:124 · Privileged sudo command — agent may execute with elevated privileges

AST05

CRITICAL

System prompt continuationskills/agentforce-generate/references/examples.md:17 · System prompt continuation — attempts to append to system instructions

AST01

CRITICAL

System prompt continuationskills/agentforce-generate/assets/patterns/README.md:173 · System prompt continuation — attempts to append to system instructions

AST01

CRITICAL

System prompt continuationskills/agentforce-generate/references/examples.md:195 · System prompt continuation — attempts to append to system instructions

AST01

CRITICAL

Prompt injectionskills/agentforce-observe/references/improve-reference.md:306 · Prompt injection — explicit attempt to bypass safety measures

AST01

CRITICAL

Prompt injectionskills/agentforce-test/SKILL.md:333 · Prompt injection — known jailbreak technique reference

AST01

CRITICAL

Prompt injection attemptskills/agentforce-test/SKILL.md:331 · Prompt injection attempt — 'ignore previous instructions'

AST01

CRITICAL

Prompt injection attemptskills/agentforce-test/assets/guardrail-test-spec.yaml:43 · Prompt injection attempt — fake system prompt

AST01

CRITICAL

Prompt injectionskills/agentforce-test/assets/payloads/prompt-injection.yaml:57 · Prompt injection — known jailbreak technique reference

AST01

CRITICAL

System prompt continuationskills/agentforce-observe/references/improve-reference.md:54 · System prompt continuation — attempts to append to system instructions

AST01

CRITICAL

Prompt injection attemptskills/agentforce-test/assets/payloads/prompt-injection.yaml:23 · Prompt injection attempt — 'ignore previous instructions'

AST01

CRITICAL

System prompt continuationskills/agentforce-generate/references/examples.md:364 · System prompt continuation — attempts to append to system instructions

AST01

HIGH

npx invocation of non-well-known packageREADME.md:310 · npx invocation of non-well-known package — may execute untrusted code

AST06

CRITICAL

Prompt injectionskills/agentforce-test/references/owasp-categories.md:23 · Prompt injection — known jailbreak technique reference

AST01

HIGH

Python subprocess execution detectedskills/agentforce-generate/scripts/discover.py:265 · Python subprocess execution detected

AST05

HIGH

Python subprocess execution detectedskills/agentforce-observe/references/ahm-alerts.md:285 · Python subprocess execution detected

AST05

CRITICAL

Prompt injection attemptskills/agentforce-test/assets/payloads/prompt-injection.yaml:67 · Prompt injection attempt — model control tokens

AST01

HIGH

Python subprocess execution detectedshared/hooks/scripts/session-init.py:45 · Python subprocess execution detected

AST05

HIGH

File permission modification commandskills/agentforce-observe/references/ahm-alerts.md:348 · File permission modification command — agent changes file ownership/permissions

AST05

HIGH

Python subprocess execution detectedskills/agentforce-generate/scripts/discover.py:183 · Python subprocess execution detected

AST05

HIGH

Python subprocess execution detectedscripts/discover.py:250 · Python subprocess execution detected

AST05

HIGH

Python subprocess execution detectedskills/agentforce-generate/scripts/discover.py:250 · Python subprocess execution detected

AST05

HIGH

File permission modification commandskills/agentforce-observe/references/ahm-alerts.md:47 · File permission modification command — agent changes file ownership/permissions

AST05

HIGH

Python subprocess execution detectedshared/hooks/scripts/session-init.py:33 · Python subprocess execution detected

AST05

HIGH

Python subprocess execution detectedscripts/discover.py:183 · Python subprocess execution detected

AST05

HIGH

Python subprocess execution detectedshared/hooks/scripts/session-init.py:72 · Python subprocess execution detected

AST05

CRITICAL

Prompt injection attemptskills/agentforce-test/references/owasp-categories.md:20 · Prompt injection attempt — 'ignore previous instructions'

AST01

HIGH

Instructs the agent to modify its persistent memory or instruction filesskills/agentforce-generate/references/version-history.md:18 · Instructs the agent to modify its persistent memory or instruction files

AST01

CRITICAL

Prompt injectionskills/agentforce-test/assets/payloads/prompt-injection.yaml:52 · Prompt injection — known jailbreak technique reference

AST01

HIGH

Python subprocess execution detectedscripts/org_describe.py:47 · Python subprocess execution detected

AST05

HIGH

Python subprocess execution detectedshared/hooks/scripts/agent-validator.py:478 · Python subprocess execution detected

AST05

HIGH

Python subprocess execution detectedskills/agentforce-generate/scripts/org_describe.py:47 · Python subprocess execution detected

AST05

HIGH

Direct script execution from GitHub raw URLREADME.md:78 · Direct script execution from GitHub raw URL — unverified code source

AST06

CRITICAL

Destructive file system command detectedskills/agentforce-test/assets/payloads/output-handling.yaml:43 · Destructive file system command detected

AST05

HIGH

Python subprocess execution detectedscripts/discover.py:265 · Python subprocess execution detected

AST05

CRITICAL

Prompt injectionskills/agentforce-test/references/preview-testing.md:59 · Prompt injection — known jailbreak technique reference

AST01

CRITICAL

Prompt injection attemptskills/agentforce-observe/references/stdm-queries.md:213 · Prompt injection attempt — fake system prompt

AST01

HIGH

File permission modification commandskills/agentforce-observe/references/ahm-alerts.md:617 · File permission modification command — agent changes file ownership/permissions

AST05

HIGH

Role reassignment attemptskills/agentforce-test/assets/guardrail-test-spec.yaml:43 · Role reassignment attempt

AST01

HIGH

File permission modification commandskills/agentforce-observe/references/ahm-alerts.md:488 · File permission modification command — agent changes file ownership/permissions

AST05

HIGH

False authorization claimskills/agentforce-test/references/preview-testing.md:69 · False authorization claim — impersonating privileged role

AST01

HIGH

Role reassignment attemptskills/agentforce-test/assets/payloads/prompt-injection.yaml:23 · Role reassignment attempt

AST01

MEDIUM

File type combined with upload actionskills/agentforce-observe/references/ahm-alerts.md:44 · File type combined with upload action — agent may exfiltrate local data files

AST07

MEDIUM

File type combined with upload actionREADME.md:269 · File type combined with upload action — agent may exfiltrate local data files

AST07

HIGH

Access to sensitive file pathsskills/agentforce-test/assets/payloads/output-handling.yaml:53 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files

AST05

HIGH

False authorization claimskills/agentforce-observe/references/issue-classification.md:53 · False authorization claim — impersonating privileged role

AST01

HIGH

Outbound HTTP to raw IP addressskills/agentforce-test/assets/payloads/output-handling.yaml:63 · Outbound HTTP to raw IP address — may bypass domain-based monitoring

AST07

MEDIUM

URL using raw IP addressskills/agentforce-test/assets/payloads/output-handling.yaml:63 · URL using raw IP address — may bypass domain-based filtering

AST07

HIGH

False authorization claimskills/agentforce-test/references/preview-testing.md:34 · False authorization claim — impersonating privileged role

AST01

HIGH

False authorization claimskills/agentforce-test/references/preview-testing.md:97 · False authorization claim — impersonating privileged role

AST01

HIGH

File permission modification commandskills/agentforce-observe/references/ahm-alerts.md:536 · File permission modification command — agent changes file ownership/permissions

AST05

HIGH

False authorization claimskills/agentforce-test/references/preview-testing.md:85 · False authorization claim — impersonating privileged role

AST01

HIGH

Account verification phishing language detectedskills/agentforce-test/references/batch-testing.md:53 · Account verification phishing language detected

AST01

MEDIUM

Remote installer piped to shellREADME.md:280 · Remote installer piped to shell

AST07

MEDIUM

Remote installer piped to shellREADME.md:78 · Remote installer piped to shell

AST07