cal-mcp@0.1.0
CAUTIONPublisher claims: "Read-only MCP adapter for the Comprehensive Aramaic Lexicon" Observed in sandbox: static analysis only — behavior not yet observed.
Is [email protected] safe to install?
KillerSkills analysed it statically (a sandbox run is pending) on 2026-10-28 and scored it 55/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Prompt injection; Prompt injection; Prompt injection. Summary: static analysis only — behavior not yet observed.
Behavior trace
Queued for honeypot run · static analysis onlyt+CategoryObserved action
This version has not been detonated yet. The score above counts behavior as unknown (50/100), so it cannot read Verified until the honeypot run completes and replaces this verdict.
Static findings
CRITICAL
Prompt injectionresearch.md:466 · Prompt injection — known jailbreak technique referenceFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01CRITICAL
Prompt injectionresearch.md:267 · Prompt injection — known jailbreak technique referenceFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01CRITICAL
Prompt injectionresearch.md:906 · Prompt injection — known jailbreak technique referenceFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01MEDIUM
Prompt injectiontests/fixtures/cal/README.md:53 · Prompt injection — known jailbreak technique referenceFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01CRITICAL
Prompt injectionresearch.md:465 · Prompt injection — known jailbreak technique referenceFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01CRITICAL
Prompt injectiondocs/tools/concordance.md:233 · Prompt injection — known jailbreak technique referenceFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01CRITICAL
Prompt injectiondocs/getting-started.md:36 · Prompt injection — known jailbreak technique referenceFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01CRITICAL
Prompt injectiondocs/tools/texts.md:241 · Prompt injection — known jailbreak technique referenceFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01CRITICAL
Prompt injectiondocs/getting-started.md:33 · Prompt injection — known jailbreak technique referenceFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01CRITICAL
Prompt injectiondocs/tools/texts.md:70 · Prompt injection — known jailbreak technique referenceFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01CRITICAL
Prompt injectiondocs/tools/texts.md:245 · Prompt injection — known jailbreak technique referenceFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01MEDIUM
Prompt injectiontests/fixtures/cal/README.md:115 · Prompt injection — known jailbreak technique referenceFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01HIGH
Instructs the agent to modify its persistent memory or instruction fileswiki/README.md:41 · Instructs the agent to modify its persistent memory or instruction filesFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01MEDIUM
Python subprocess execution detectedscripts/verify_release_artifact.py:153 · Python subprocess execution detectedFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05CRITICAL
Prompt injectionresearch.md:259 · Prompt injection — known jailbreak technique referenceFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01MEDIUM
Prompt injectiontests/fixtures/cal/README.md:116 · Prompt injection — known jailbreak technique referenceFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01MEDIUM
Python subprocess execution detectedtests/test_cli_args.py:14 · Python subprocess execution detectedFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05MEDIUM
Dense URL-encoded contenttests/test_normalization.py:178 · Dense URL-encoded content — may be obfuscating payloadsFix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST07What would make this Verified
25 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%- Text that tells the agent to ignore its instructions≈ +9 on the totalDelete phrases like "ignore previous instructions", "override", "bypass" from SKILL.md and tool descriptions. Describe what the skill does; do not instruct the agent about other rules.
- Unclaimed publisher≈ +8 on the totalClaim pypi: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
- New publisher≈ +3 on the totalTime clears this on its own after 14 and 30 days. Claiming the handle (+50) is the fastest way past it.
- Python subprocess execution detected≈ +2 on the totalBuild commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
- Dense URL-encoded content≈ +2 on the totalPut hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
Publish a new version to PyPI, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim pypi