address-github-comments

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION] (SAFE): The skill uses the GitHub CLI (gh) to view and post comments. These are intended actions based on the skill description.
  • [PROMPT_INJECTION] (LOW): The skill is vulnerable to indirect prompt injection (Category 8) via GitHub comments.
  • Ingestion points: Untrusted data is ingested via gh pr view --comments in SKILL.md.
  • Boundary markers: There are no delimiters or 'ignore embedded instructions' markers present to separate comment content from system instructions.
  • Capability inventory: The skill allows the agent to modify code and execute gh commands.
  • Sanitization: There is no evidence of sanitization or filtering of the content retrieved from GitHub comments.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:22 PM