analyze
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze external documentation files, which creates a potential surface for indirect prompt injection.
- Ingestion points: The skill reads multiple markdown files from the
02-DOCS/wiki/sdd/directory, includingconstitution.md, specifications, plans, and task lists, as well asuser-profile.mdandconfig.yaml. - Boundary markers: The instructions do not define explicit string delimiters for the ingested content, though they provide a strong logical constraint requiring the agent to only report findings without modifying source artifacts.
- Capability inventory: The skill possesses the ability to write new markdown files (
02-DOCS/wiki/sdd/analysis/<slug>.md) and modify the project's knowledge map (02-DOCS/wiki/index.md). - Sanitization: There is no evidence of explicit sanitization or escaping of the content read from external markdown files before processing.
Audit Metadata