skills/firecrawl/openclaw/github/Gen Agent Trust Hub

github

Pass

Audited by Gen Agent Trust Hub on Sep 17, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests and processes untrusted data from GitHub (e.g., issue descriptions, pull request bodies, and CI logs).
  • Ingestion points: Data enters the agent context through commands like gh pr view, gh issue list, gh run view, and gh api as documented in SKILL.md.
  • Boundary markers: The instructions do not specify any delimiters or safety markers to differentiate between user-provided data and agent instructions.
  • Capability inventory: The skill allows the agent to perform write operations such as gh pr create/merge, gh issue create/close, and arbitrary API calls via gh api as documented in SKILL.md.
  • Sanitization: There are no explicit sanitization or validation steps mentioned for the content retrieved from external sources.
  • [SAFE]: The skill uses the official GitHub CLI (gh), which is a well-known service. The installation methods (Homebrew and APT) specified in the YAML frontmatter target official package registries and are consistent with standard development practices.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 17, 2026, 07:53 PM
Security Audit — agent-trust-hub — github