sop-writer
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill provides a prompt template to help users structure process descriptions into Standard Operating Procedures. It does not include any executable scripts or request access to external tools.
- [NO_CODE]: The skill consists entirely of markdown instructions and prompt templates, with no executable scripts or binaries provided.
- [INDIRECT_PROMPT_INJECTION]: The skill features a data ingestion surface where user-provided process descriptions are interpolated into a prompt.
- Ingestion points: User-supplied rough process description specified in
SKILL.md. - Boundary markers: None; user content is placed directly within bracketed placeholders in the prompt template.
- Capability inventory: None; the skill does not define or use any tools or perform system operations.
- Sanitization: None; the skill relies on the underlying LLM's own safety guardrails.
Audit Metadata