devrel-content
Pass
Audited by Gen Agent Trust Hub on Oct 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to read an external context file to determine the audience's role and technical background. This dependency on external data represents an ingestion point for potentially untrusted data that could influence the agent's output.\n
- Ingestion points: The agent is directed to read
.agents/developer-audience-context.mdat the start of the content creation process (referenced inSKILL.md).\n - Boundary markers: No explicit delimiters or instructions are provided to the agent to treat the contents of the context file as potentially untrusted or to ignore embedded instructions within it.\n
- Capability inventory: The skill enables the agent to generate technical blog posts, guides, and executable code snippets in languages including JavaScript, Python, Go, and Rust.\n
- Sanitization: No methods for validating, filtering, or sanitizing the data read from the audience context file are described in the instructions.
Audit Metadata