skills/iankiku/forwward-teams/vet/Gen Agent Trust Hub

vet

Pass

Audited by Gen Agent Trust Hub on Aug 31, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses Git and GitHub CLI commands (such as git rev-list, git cat-file, git diff, and gh run list) to audit the state of a repository. These commands are used for inspection purposes and do not modify the system or repository state.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests data from external sources, specifically Git logs and GitHub CI statuses.
  • Ingestion points: Data enters the context through git log, git rev-list, and gh run list output in SKILL.md Step 1.
  • Boundary markers: None present; the skill treats command output as direct data for the report.
  • Capability inventory: The skill uses Git and GitHub CLI tools for read-only operations. It does not perform file-writes, arbitrary code execution, or non-whitelisted network operations.
  • Sanitization: No specific sanitization or filtering of commit messages or branch names is mentioned.
  • Risk Assessment: The risk is minimal because the skill is explicitly read-only and its purpose is to generate a report for a human operator.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 31, 2026, 01:54 AM
Security Audit — agent-trust-hub — vet