cw-promise
Pass
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTION
Full Analysis
- [NO_CODE]: The skill consists entirely of natural language instructions and does not include any scripts, executable code, or package dependencies.
- [INDIRECT_PROMPT_INJECTION]: The skill identifies a surface for indirect prompt injection via user-supplied context. 1. Ingestion points: User-provided topic or context via the /cw-promise command in SKILL.md. 2. Boundary markers: The prompt does not define explicit delimiters or instructions to ignore embedded commands for the context variable. 3. Capability inventory: The skill has no capabilities to execute code, perform network operations, or write files. 4. Sanitization: No input sanitization or validation is performed on the user context. Analysis: Because the skill lacks any functional capabilities, the inclusion of unvetted user input in the prompt carries no significant security risk.
Audit Metadata