ps-no-comments
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted input in the form of code files and git diffs, which could contain malicious instructions designed to influence the agent's behavior.\n
- Ingestion points: The skill ingest data from the "caller's files or diff" as defined in the Scope section.\n
- Capability inventory: The skill can spawn subagents, invoke other commands (/ps-how, /ps-why, /ps-architect), and perform write operations to the file system to implement fixes and remove comments.\n
- Boundary markers: The instructions lack explicit boundary markers or delimiters to isolate untrusted code content from the agent's control logic.\n
- Sanitization: There is no evidence of input sanitization or validation to filter out potential prompt injection attacks embedded in the source code comments it processes.
Audit Metadata