respond-pr-feedback

Pass

Audited by Gen Agent Trust Hub on Apr 3, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests and processes untrusted data from external PR comments.\n
  • Ingestion points: Pull request comments are fetched using gh api in SKILL.md.\n
  • Boundary markers: Absent. There are no instructions to use delimiters or ignore embedded commands within the fetched comments.\n
  • Capability inventory: The agent has the ability to post new comments (gh api POST) and resolve discussion threads via GraphQL mutations in SKILL.md.\n
  • Sanitization: Absent. The skill does not specify any validation or sanitization for the comment content before processing it for response generation.\n- [COMMAND_EXECUTION]: The skill uses the GitHub CLI (gh) to perform repository operations. While these are legitimate tools, the integration with external user input (PR comments) used to generate command arguments creates a potential injection surface if the agent output is not handled securely by the underlying platform.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 3, 2026, 04:17 AM