pr-review-navigator

Pass

Audited by Gen Agent Trust Hub on May 16, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADSDATA_EXFILTRATION
Full Analysis
  • [PROMPT_INJECTION]: The skill presents a surface for indirect prompt injection as it processes untrusted data (titles, descriptions, and code) from GitHub pull requests.
  • Ingestion points: External data is fetched using gh pr view and gh pr diff as described in SKILL.md.
  • Boundary markers: The instructions do not specify the use of boundary markers or delimiters to isolate untrusted PR content from the agent's core instructions.
  • Capability inventory: The agent has the ability to post comments back to GitHub via gh pr comment and write to the local file system (pr-review-navigator.md).
  • Sanitization: No explicit sanitization or validation of the ingested PR content is performed before it is used to generate summaries or diagrams.
  • [COMMAND_EXECUTION]: The skill relies on shell commands including gh, git, and shasum to perform its primary functions. These commands are standard for repository management and pull request analysis.
  • [EXTERNAL_DOWNLOADS]: The skill communicates with GitHub's official infrastructure to retrieve pull request metadata and file differences.
  • [DATA_EXFILTRATION]: The skill is designed to transmit generated analysis back to GitHub by posting pull request comments, which is its intended primary output mechanism.
Audit Metadata
Risk Level
SAFE
Analyzed
May 16, 2026, 05:38 AM
Security Audit — agent-trust-hub — pr-review-navigator