review-readmes
Pass
Audited by Gen Agent Trust Hub on Jul 3, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it processes untrusted content from repository README files.
- Ingestion points: The skill uses find to locate and then reads the full content of all README.md files (SKILL.md).
- Boundary markers: Absent. The instructions do not define delimiters for the ingested content or warn the agent to ignore instructions found within the README files.
- Capability inventory: The agent uses find (shell execution) and is instructed to apply fixes directly to files (file system modification).
- Sanitization: There is no evidence of sanitization or filtering of the content read from the files.
- [COMMAND_EXECUTION]: The skill executes the find command to locate documentation files. This is a standard and benign use of system tools for its stated purpose.
Audit Metadata