skills/ibm/fp-go/fp-go-pr-review/Gen Agent Trust Hub

fp-go-pr-review

Pass

Audited by Gen Agent Trust Hub on Aug 7, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill contains functional programming guidelines and code review checklists for the IBM fp-go library. All code samples and references are consistent with the stated purpose of improving code quality.
  • [COMMAND_EXECUTION]: The skill uses git diff and gh pr commands to facilitate the review process. These are standard operations for development workflows and are scoped to the user's active repository and PR context.
  • [EXTERNAL_DOWNLOADS]: References to github.com/IBM/fp-go/v2 and documentation are provided. These target official resources from the skill's author (IBM) and are categorized as safe configuration and dependency references.
  • [PROMPT_INJECTION]: The skill processes untrusted data from pull request diffs (git diff). This constitutes an indirect prompt injection surface (Category 8).
  • Ingestion points: PR changes retrieved via git diff in SKILL.md (Review Process).
  • Boundary markers: Absent; the instructions do not specify delimiters to isolate PR code from the agent's instructions.
  • Capability inventory: The skill can post comments and annotations via gh pr review and gh api in SKILL.md (Submit Findings).
  • Sanitization: Absent; the instructions do not require escaping or validation of the PR content before analysis.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 7, 2026, 10:18 AM
Security Audit — agent-trust-hub — fp-go-pr-review