technical-writing
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructions and integration examples describe a workflow that ingests external, untrusted content to generate documentation, creating a surface for indirect prompt injection attacks.
- Ingestion points: The skill (specifically the 'Agent Integration' section in SKILL.md) describes ingesting data from source files such as 'src/services/PaymentService.ts' and documentation files like 'README.md' and 'docs/api.md'.
- Boundary markers: The instructions do not define delimiters or provide specific warnings to the agent to ignore instructions embedded within the ingested data.
- Capability inventory: While the skill itself consists only of Markdown instructions without executable scripts, it defines workflows for task execution and documentation generation, implying a read-then-output capability chain.
- Sanitization: The skill lacks explicit instructions for sanitizing or validating external input before it is incorporated into the generated content.
Audit Metadata