find-verification-tools

Pass

Audited by Gen Agent Trust Hub on Aug 18, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill directs the agent to locate and follow instructions in project-controlled files like README.md, AGENTS.md, and CLAUDE.md, which creates an indirect prompt injection surface. Attackers could place malicious instructions in these files to hijack the agent's behavior during code verification.
  • Ingestion points: Project documentation (README.md, AGENTS.md, CLAUDE.md), CI configuration files (.gitlab-ci.yml, .github/workflows/), and dependency manifests (package.json, Gemfile, pyproject.toml).
  • Boundary markers: No specific delimiters or instructions to ignore embedded commands are provided to the agent for processing these files.
  • Capability inventory: The agent is tasked with identifying and potentially executing CLI commands derived from these untrusted sources.
  • Sanitization: The skill does not prescribe any validation or sanitization for the commands discovered in the project files.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 18, 2026, 05:11 PM
Security Audit — agent-trust-hub — find-verification-tools