content-repurposing
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted external data such as source URLs and transcripts, which introduces a potential surface for indirect prompt injection.
- Ingestion points: The skill identifies its inputs as 'Source URLs, transcripts, posts, research reports, or owned source material' in SKILL.md.
- Boundary markers: The workflow does not describe the use of explicit delimiters or specific 'ignore instructions' to separate ingested source material from the agent's core instructions.
- Capability inventory: The skill orchestrates multiple downstream tools including 'transcript-intelligence', 'scrapecreators-api', and various platform-specific content generators across SKILL.md and skill.meta.json.
- Sanitization: There is no explicit mention of sanitizing or escaping extracted 'content atoms' before they are processed and repurposed into final platform-ready drafts.
- [SAFE]: The installation instructions using 'npx goose-skills' and the required skills such as 'transcript-intelligence' and 'goose-graphics' are official resources provided by the vendor ecosystem and represent expected functionality for this skill's use case.
Audit Metadata