b2-english-writing
Pass
Audited by Gen Agent Trust Hub on Nov 2, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill provides instructions for writing at a B2 level and does not perform network operations or access sensitive data.
- [COMMAND_EXECUTION]: A local bash script
scripts/review-length.shusesawkto count words in prose. It follows secure practices by quoting variables and checking file existence before processing user-provided files. - [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted user content for rewriting and has the capability to write files. This represents a standard surface for indirect prompt injection common to writing assistants. 1. Ingestion points: User-provided text in SKILL.md Step 1. 2. Boundary markers: None. 3. Capability inventory: File writing in SKILL.md Step 6. 4. Sanitization: None.
Audit Metadata