write-article-complete
Pass
Audited by Gen Agent Trust Hub on Oct 25, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill facilitates an automated workflow that ingests untrusted user input and processes it through a chain of sub-skills that perform file system operations (creation, reading, and editing). It explicitly instructs the agent to bypass user confirmation between stages ("Do not stop for confirmation between stages", "Do not ask the user whether to apply the fixes"), which removes human oversight from the write-review-apply cycle.
- Ingestion points: Processes user requests and provided context in
SKILL.mdduring the 'Create' stage. - Boundary markers: None identified to separate user content from system instructions or to ignore embedded commands.
- Capability inventory: The skill orchestrates
write-article,write-review, andwrite-review-apply, which possess capabilities to create, read, and modify files on the local filesystem. - Sanitization: No evidence of sanitization or validation of the input content before it is passed to subsequent tools or used to modify files.
Audit Metadata