closer-critique
Pass
Audited by Gen Agent Trust Hub on Sep 3, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external draft content, which is an untrusted data source.\n
- Ingestion points: Input is defined as the last paragraph and frontmatter of a draft in SKILL.md.\n
- Boundary markers: The skill does not define specific boundaries or markers to isolate the draft content from the agent's instructions.\n
- Capability inventory: The skill is limited to text evaluation and does not possess capabilities for file modification, network access, or command execution.\n
- Sanitization: No input validation or sanitization logic is present.\n- [NO_CODE]: The skill is entirely composed of Markdown text and does not include any executable code, scripts, or package dependencies.
Audit Metadata