numbers-in-narrative
Pass
Audited by Gen Agent Trust Hub on Aug 14, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: The skill consists entirely of markdown documentation and a JSON rubric. There are no executable files (such as .py, .js, or .sh) or platform-specific command configurations that would trigger execution of code.
- [INDIRECT_PROMPT_INJECTION]: The skill provides instructions for processing user-supplied prose and quantitative data. While this creates a theoretical attack surface, the risk is negligible as the skill defines no exploitable capabilities. * Ingestion points: User-provided drafts, statistics, and source documentation pointers defined in SKILL.md (Workflow Steps 2 and 3). * Boundary markers: Absent; the skill does not specify the use of delimiters or 'ignore' instructions for user-provided content. * Capability inventory: None; the skill does not request or use any external tools, APIs, or system commands. * Sanitization: Absent; the instructions do not include methods for filtering or escaping input data.
- [SAFE]: No evidence of obfuscation, credential exposure, or persistence mechanisms was found in the provided files. All referenced resources are local to the skill package.
Audit Metadata