rtfm
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill requires the agent to analyze and report on work performed, such as code changes and command outputs, which may contain malicious instructions embedded in the data.
- Ingestion points: The skill instructs the agent to inspect diffs, command outputs, and reports generated during previous work (SKILL.md).
- Boundary markers: There are no instructions to use delimiters or ignore instructions embedded within the processed work data.
- Capability inventory: The skill anticipates the agent running shell commands (e.g., 'npm test') and inspecting the file system (SKILL.md).
- Sanitization: No sanitization or validation of the ingested work data is mentioned before processing.
- [EXTERNAL_DOWNLOADS]: The skill references an external repository at 'github.com/mattpocock/skills' as an upstream source for productivity logic, representing a reference to third-party content.
- [COMMAND_EXECUTION]: The instructions explicitly direct the agent to execute tests and inspections (e.g., 'npm test') to verify work results before making recommendations.
Audit Metadata