no-comments
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external data in the form of code diffs and files, creating a surface for indirect prompt injection if those files contain malicious instructions.\n
- Ingestion points: The skill reads "The caller's files or diff" as specified in SKILL.md and "current diff against the base branch" in references/no-comments-procedure.md.\n
- Boundary markers: The skill implements a process-based boundary by spawning a "read-only review subagent" (SKILL.md) to generate a report, which the main agent then inspects before performing any modifications.\n
- Capability inventory: The skill possesses the capability to modify the local file system to "delete accepted comments and apply root-cause fixes" (SKILL.md).\n
- Sanitization: There is no evidence of explicit sanitization or filtering of the code content before it is processed by the agent or subagent.\n- [SAFE]: The skill documentation and metadata correctly attribute its origins to well-known repositories and organizations.\n
- The skill fetches its logic and guidelines from established sources such as the Cursor plugins repository and the open-pstack project, as documented in the README.md and SKILL.md metadata.
Audit Metadata