find-ideas
Pass
Audited by Gen Agent Trust Hub on Oct 10, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted external content from social media platforms, creating a vulnerability surface where instructions embedded in processed data could influence the agent.
- Ingestion points: According to
SKILL.md, the skill reads reel URLs, saved transcripts, on-screen text, and niche creator posts. - Boundary markers: The instructions do not define specific delimiters (like triple backticks or XML tags) or provide explicit directives for the agent to ignore instructions embedded within the processed transcripts or on-screen text.
- Capability inventory: The skill produces a list of ideas that are subsequently handed to the
write-scriptskill and references theedit-videoskill, suggesting it operates within an automated content creation pipeline. - Sanitization: There is no mention of sanitizing or filtering external content before it is processed or passed to downstream scripts.
Audit Metadata