plan-newsletter
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external sources provided by the user, which presents an attack surface for instructions embedded in that data.\n
- Ingestion points: Ingests topic ideas, video transcripts, existing notes, research, and content from URLs or documents provided by the user (SKILL.md).\n
- Boundary markers: The instructions do not define clear delimiters or specify that the agent should ignore instructions found within the user-provided content.\n
- Capability inventory: The skill writes a structured plan to the local file system at
./newsletter/issues/[issue_name]/plan.mdand invokes several tools (creator-stack:research,creator-stack:write, etc.).\n - Sanitization: There is no evidence of sanitization, filtering, or validation of the ingested user content before it is passed to the orchestration workflow.
Audit Metadata