no-comments
Pass
Audited by Gen Agent Trust Hub on Oct 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted code from caller files or diffs, which serves as a vector for indirect prompt injection where embedded instructions could influence the agent's behavior during comment cleanup or code modification.
- Ingestion points: The skill explicitly ingests 'the caller's files or diff' as its primary data source (SKILL.md).
- Boundary markers: There are no instructions to use delimiters or to treat the content of the processed files as untrusted data, which may lead the agent to follow instructions contained within the code comments it is supposed to analyze.
- Capability inventory: The agent is authorized to spawn subagents ('pstack:comment-sicko'), execute analysis tools (/how, /why), and implement code changes (deletions and fixes) based on the processed data.
- Sanitization: The skill does not define any sanitization or validation steps for the input code before it is passed to the subagent or used to drive execution logic.
Audit Metadata