address-github-comments

Pass

Audited by Gen Agent Trust Hub on Mar 10, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection through external data. 1. Ingestion points: Untrusted data is retrieved from GitHub using gh pr view --comments in SKILL.md. 2. Boundary markers: Absent; there are no instructions or delimiters provided to the agent to distinguish between its instructions and the content of the comments. 3. Capability inventory: The agent is instructed to "Apply the code changes" and can post responses using gh pr comment as defined in SKILL.md. 4. Sanitization: Absent; the instructions do not include steps to validate or filter the external content before processing it.
  • [COMMAND_EXECUTION]: The skill utilizes the GitHub CLI (gh) for authentication and pull request interactions. These commands are standard for the skill's purpose and do not represent a security risk within this context.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 10, 2026, 01:14 AM