technical-writing
Pass
Audited by Gen Agent Trust Hub on Aug 28, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process untrusted external content, such as PR descriptions, RFCs, and READMEs, which creates a surface for indirect prompt injection if the input text contains malicious instructions aimed at the agent.
- Ingestion points: Processes external prose in documents, RFCs, readmes, PR descriptions, and commit messages as defined in the skill scope.
- Boundary markers: The skill does not specify the use of delimiters or 'ignore' instructions to isolate processed text from the agent's core logic.
- Capability inventory: The agent is instructed to perform text transformations and potentially update rule lists in a secondary skill (unslop).
- Sanitization: No explicit sanitization or validation of external content is described.
Audit Metadata