write-longform
Pass
Audited by Gen Agent Trust Hub on Aug 21, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: The skill consists entirely of natural language instructions for text generation and logical structuring. It does not request any sensitive permissions or external tool access.
- [NO_CODE]: There are no scripts (Python, Node.js, Shell) or binaries associated with this skill. It relies purely on the agent's internal reasoning capabilities.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process user-provided data such as facts and personal experience. While this represents a potential data ingestion surface, the risk is negligible as the skill lacks any technical capabilities (e.g., file writing, network requests, tool execution) that an injection could exploit.
- Ingestion points: User-supplied experience and observed facts (SKILL.md).
- Boundary markers: The instructions explicitly forbid the use of invented citations or authorities, though no technical delimiters are defined for the input data.
- Capability inventory: None. The skill does not use any tools or system commands.
- Sanitization: None required as the output is restricted to natural language text.
Audit Metadata