headlines-and-titles
Pass
Audited by Gen Agent Trust Hub on Oct 28, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: No malicious patterns or security risks were identified. The skill consists of natural language instructions for title and headline generation.
- [INDIRECT_PROMPT_INJECTION]: The skill possesses a data ingestion surface as it processes user-supplied drafts or summaries ('The piece') to perform its primary function.
- Ingestion points: User-provided content described in the 'What to ask for' section of SKILL.md.
- Boundary markers: None explicitly defined in the instructions to protect against instructions within the provided text.
- Capability inventory: The skill mentions the ability to interact with a connected notes application or connector to save output (referenced in SKILL.md).
- Sanitization: No specific sanitization or filtering of input content is mandated.
- Risk Assessment: The risk is negligible as the agent is strictly directed to produce specific headline styles and follow a specific markdown format.
Audit Metadata