react-effects-audit
Pass
Audited by Gen Agent Trust Hub on Sep 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill scans and reads content from user-provided source code files (*.tsx, *.jsx, *.ts, *.js) to perform context analysis and detect anti-patterns. This represents an ingestion point for untrusted data that could contain malicious instructions designed to influence the agent's behavior during the reporting phase.
- Ingestion points: Target files matched by the glob pattern in
SKILL.md(Phase 1) and subsequently read for context analysis (Phase 3). - Boundary markers: The skill instructions do not include explicit delimiters or warnings to treat the read file content strictly as data, which may allow embedded instructions to be followed by the agent.
- Capability inventory: The skill is primarily read-only, focusing on file reading and generating an audit report. It does not explicitly call network tools or file-write operations within the provided skill body, which limits the potential impact of an injection.
- Sanitization: There is no evidence of sanitization, escaping, or filtering of the external source code content before it is processed by the agent.
Audit Metadata