collection-storytelling
Pass
Audited by Gen Agent Trust Hub on Mar 5, 2026
Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
- [PROMPT_INJECTION]: The skill architecture establishes a surface for indirect prompt injection by design. \n
- Ingestion points: The skill references external data from
src/feedops/config/collection_stories.yamland a 41-collection CSV file. \n - Boundary markers: There are no specific delimiters or instructions to treat external data as untrusted content defined in the skill. \n
- Capability inventory: This skill is strictly instructional and does not define any subprocess, network, or file-system capabilities. \n
- Sanitization: No sanitization or validation procedures for the ingested data are specified.\n- [NO_CODE]: The skill consists entirely of Markdown instructions and does not include any executable scripts, binaries, or code files.
Audit Metadata