security-best-practices

Pass

Audited by Gen Agent Trust Hub on Sep 7, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill's primary function is to ingest and analyze files from a user's repository to provide security feedback. The SKILL.md instructions include an "Overrides" section that explicitly tells the agent to follow project-specific documentation even if it requires bypassing security best practices. This design choice creates a significant surface for indirect prompt injection, as an attacker could influence the agent's behavior by placing malicious instructions within the repository's documentation or prompt files.
  • Ingestion points: Repository source code, documentation files, and project-specific prompt files.
  • Boundary markers: The skill does not provide instructions for the agent to use delimiters or specific safety prompts to isolate and disregard instructions embedded in the analyzed data.
  • Capability inventory: The skill utilizes capabilities to read files, generate markdown reports, and propose or implement code fixes.
  • Sanitization: No sanitization or filtering of instructions found within repo-level data is defined in the skill's logic.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 7, 2026, 02:48 PM
Security Audit — agent-trust-hub — security-best-practices