social-content
Pass
Audited by Gen Agent Trust Hub on Apr 7, 2026
Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
- [PROMPT_INJECTION]: The skill defines workflows for the agent to process external, untrusted content including video transcripts and scraped social media posts. This creates a potential surface for indirect prompt injection where malicious instructions embedded in the input data could attempt to subvert the agent's behavior.\n
- Ingestion points: Video and podcast transcripts mentioned in the repurposing workflow (SKILL.md) and scraped posts from third-party tools mentioned in the reverse engineering guide (references/reverse-engineering.md).\n
- Boundary markers: The instructions do not provide explicit delimiters or instructions for the agent to ignore embedded commands within the processed data.\n
- Capability inventory: The skill itself contains no executable code; it relies on the agent's existing file-reading and data processing capabilities.\n
- Sanitization: There are no instructions for sanitizing or validating the content of the external data before analysis.\n- [NO_CODE]: The provided skill package consists entirely of markdown documentation, reference guides, and JSON evaluation data. It does not include any executable scripts (e.g., .py, .js, .sh) or compiled binaries.
Audit Metadata