technical-writing
Pass
Audited by Gen Agent Trust Hub on Oct 5, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to ingest and establish 'available source evidence' to generate technical documents. This creates a surface where instructions hidden within the source data could potentially influence the agent's writing style or content.
- Ingestion points: Uses 'available source evidence' as the basis for writing tutorials, how-to guides, and reference documents (SKILL.md).
- Boundary markers: The instructions do not define specific delimiters or security boundaries to isolate the source evidence from the agent's core instructions.
- Capability inventory: The skill's primary focus is text generation and document structure; no high-risk capabilities like network access, file system modifications, or arbitrary code execution are requested or used.
- Sanitization: The skill includes a requirement to 'Verify source-backed statements and label inference,' which serves as a factual check but is not a dedicated security sanitization measure against adversarial injection.
Audit Metadata