skill-publish-checklist
Pass
Audited by Gen Agent Trust Hub on Sep 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process untrusted content from user-provided text and project files such as meta.json, creating a surface where malicious data could attempt to override agent instructions. 1. Ingestion points: The agent is instructed to read contents from user-specified output directories and metadata files. 2. Boundary markers: The instructions lack specific delimiters or isolation techniques to distinguish untrusted data from command context. 3. Capability inventory: The agent reads local files and formats the findings into a JSON report. 4. Sanitization: No sanitization, validation, or escaping of the ingested content is defined in the workflow.
- [NO_CODE]: No executable scripts or compiled binaries were found in the skill package; it relies entirely on natural language instructions.
Audit Metadata