javascript-engineering
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to process and analyze content from project files such as
package.json,README.md, and source code. This creates a surface where malicious instructions embedded in these files could potentially influence agent behavior. - Ingestion points: The operating procedure in
SKILL.mdrequires the agent to 'Inspect the repository' and 'Read package.json, the relevant source files'. - Boundary markers: The skill includes a dedicated 'Security at runtime boundaries' section, explicitly directing the agent to treat external responses and request parameters as untrusted.
- Capability inventory: The agent has the ability to implement code changes, run test scripts, and perform code reviews.
- Sanitization: The skill explicitly mandates the use of parameterized APIs, safe sinks, and output encoding to handle external data correctly.
Audit Metadata