skill-from-notebook
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external sources to generate executable instructions, creating a surface for indirect prompt injection attacks where malicious content in a source document could influence agent behavior.
- Ingestion points: According to the 'Supported Input Types' table in
SKILL.md, the skill ingests data from Web URLs, local files (PDF, Word, Markdown), and YouTube subtitles. - Boundary markers: The provided instructions do not include specific delimiters or 'ignore' commands to help the agent distinguish between the skill's own instructions and potentially malicious instructions embedded in the source material.
- Capability inventory: The skill possesses the capability to generate structured markdown instructions ('Skills') which are then used to direct future agent actions.
- Sanitization: There is no evidence of input validation, filtering, or escaping mechanisms to sanitize the external content before it is interpolated into the generated output templates.
Audit Metadata