enhance-agent-guardrails
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill's primary function is to enhance repository security through standard DevSecOps practices. All identified operations are consistent with the stated purpose of auditing and securing a software repository.
- [INDIRECT_PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection as it reads project metadata and configuration files to determine the existing security stack.
- Ingestion points: Reads
package.json,.github/workflows/,.husky/,.cursor/rules/,AGENTS.md,CLAUDE.md, and.pre-commit-config.yamlto detect existing protections. - Boundary markers: The instructions do not specify the use of delimiters or 'ignore instructions' warnings when reading these files.
- Capability inventory: The skill uses
cat,ls, andrgfor information gathering and instructs the agent to install hooks, policy files, and CI gates which involve file system writes and CI configuration modifications. - Sanitization: No specific sanitization or escaping of the ingested file content is mentioned before processing.
Audit Metadata