critical-issues-only
Pass
Audited by Gen Agent Trust Hub on Aug 24, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process external, untrusted data in the form of pull request diffs.
- Ingestion points: Pull request content is ingested for review as described in
SKILL.md. - Boundary markers: No explicit boundary markers or instructions to ignore embedded commands in the PR are provided.
- Capability inventory: No scripts or tool definitions were found that execute subprocesses, perform network operations, or write to the file system.
- Sanitization: No input validation or escaping mechanisms are defined for the ingested PR content.
- [SAFE]: The version metadata references the author's repository on GitHub (
github.com/thrillmade/agent-skills), which is a standard practice for tracking skill updates and represents the vendor's own infrastructure.
Audit Metadata