audit-security
Pass
Audited by Gen Agent Trust Hub on Aug 31, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill is a defensive tool designed for auditing code for vulnerabilities. It correctly identifies security best practices (e.g., using parameterized queries, sanitizing HTML) and uses well-known, trusted resources like OWASP for research.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from external search results and the project's source code, creating a surface for potential injection.
- Ingestion points: The skill retrieves web search results and scrapes content via
firecrawl_searchandfirecrawl_scrape(SKILL.md), and reads application source code for auditing. - Boundary markers: Absent. There are no explicit instructions to use delimiters or "ignore instructions" tags when processing external data.
- Capability inventory: The skill is authorized to run local dependency audit tools (e.g.,
npm audit,pip-audit,cargo audit) and search production error logs via Sentry. - Sanitization: Absent. The skill does not describe any specific sanitization or validation of external content before the agent evaluates it. However, given the context of a security audit where data is analyzed rather than executed, this is considered a low-risk surface.
Audit Metadata