codex-review-backlog

Pass

Audited by Gen Agent Trust Hub on Aug 15, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes a local shell script located at scripts/agent-identity.sh to generate identity headers. It also uses the GitHub CLI (gh) and git for repository management, including potentially destructive operations like git reset --hard.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection (Category 8) as it ingests and acts upon external data from GitHub PR comments.
  • Ingestion points: Reads PR comments and review summaries using gh api repos/{owner}/{repo}/pulls/<n>/comments and reviews.
  • Boundary markers: None explicitly defined in the instructions to separate external comment content from agent instructions.
  • Capability inventory: Performs git reset, git push, gh api calls to create/update PRs and comments, and executes bash scripts/agent-identity.sh.
  • Sanitization: No specific sanitization or validation of the comment content is mentioned before it influences the triage and fix process.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 15, 2026, 10:26 PM
Security Audit — agent-trust-hub — codex-review-backlog