comprehensive-type-annotations
Pass
Audited by Gen Agent Trust Hub on Mar 3, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The SKILL.md file contains a mandatory memory protocol that instructs the agent to execute the shell command
cat .claude/context/memory/learnings.md. This pattern encourages the agent to use subprocess calls to read internal state or potentially sensitive historical data stored in the hidden .claude directory. - [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection because it processes untrusted external data with high-privilege tools.
- Ingestion points: The skill targets all Python files (
**/*.py) within the workspace as defined in theglobsfield of SKILL.md. - Boundary markers: There are no explicit delimiters or instructions provided to the agent to treat the code content as data only or to ignore instructions embedded within comments or docstrings in the Python files being reviewed.
- Capability inventory: The skill is granted
Read,Write, andEdittool permissions in SKILL.md, and thescripts/main.cjsfile performs file system operations. - Sanitization: There is no evidence of sanitization, escaping, or validation logic to filter out malicious prompts that might be hidden within the Python source code processed by the agent.
Audit Metadata