checking-pr-readiness

Pass

Audited by Gen Agent Trust Hub on Oct 9, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill analyzes untrusted data from the repository, including git diffs, changelogs, and issue descriptions, to provide PR readiness recommendations. This creates a surface where maliciously crafted repository content could influence the agent's assessment or verdict.
  • Ingestion points: SKILL.md (Steps 1, 2, 4, 6) reads the working surface, repository configuration, issue trackers, and branch diffs.
  • Boundary markers: The skill does not employ explicit delimiters or instruction-bypass warnings when presenting repository data to the model for judgment.
  • Capability inventory: Execution of bundled shell scripts, reading filesystem content, and running git commands.
  • Sanitization: references/identity-and-argv.md contains procedures for sanitizing the final evidence pack to exclude sensitive or local-only data.
  • [COMMAND_EXECUTION]: The skill executes local shell scripts included in the package (scripts/surface-report.sh, scripts/changelog-union.sh, and scripts/evidence-freshness.sh) to perform git operations and file analysis.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 9, 2026, 08:28 PM