skills/kriscard/skills/pr-review/Gen Agent Trust Hub

pr-review

Pass

Audited by Gen Agent Trust Hub on Jul 15, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes standard version control and repository management commands using git and gh (GitHub CLI) to retrieve diffs and PR metadata. These are appropriate for the skill's stated purpose and use standard arguments for context acquisition.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests and processes untrusted data from external sources (pull request titles, descriptions, and code comments).
  • Ingestion points: The gh pr view and gh pr diff commands in SKILL.md retrieve external content that the agent then analyzes.
  • Boundary markers: Absent. The instructions do not specify delimiters or provide a warning to the agent to ignore potentially malicious instructions embedded within the PR data.
  • Capability inventory: The agent uses git and gh CLI tools to read repository state; it does not demonstrate capabilities for file writing or arbitrary network exfiltration.
  • Sanitization: Absent. PR content is passed directly to the analysis step without filtering or escaping.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 15, 2026, 09:09 PM
Security Audit — agent-trust-hub — pr-review