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
Risk Level
SAFE
Analyzed
Jul 3, 2026, 11:04 AM
Security Audit — agent-trust-hub — review-readmes