write-goal
Pass
Audited by Gen Agent Trust Hub on Nov 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes potentially untrusted data from multiple sources to draft a standalone goal.
- Ingestion points: The skill reads Manifests, Tickets, handoffs, and other requests either as inline text or via file paths provided in the arguments (SKILL.md).
- Boundary markers: The instructions do not specify the use of delimiters or instructions to ignore embedded directives for the external content being processed.
- Capability inventory: The skill possesses file-reading capabilities to 'Read all of them and the references' and can invoke other skills like 'figure-out' (SKILL.md).
- Sanitization: There is no evidence of sanitization, filtering, or validation of the content ingested from the external sources.
Audit Metadata