outcome-review
Pass
Audited by Gen Agent Trust Hub on Nov 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill possesses an attack surface for indirect prompt injection as it ingests data from external sources and project files to update central registries.
- Ingestion points: User-provided initiative names and external document content referenced via
@filesyntax in SKILL.md. - Boundary markers: The instructions do not specify the use of delimiters or boundary markers when interpolating untrusted data into the outcome review or registry updates.
- Capability inventory: The skill utilizes file-writing capabilities to update markdown files (e.g.,
context/learnings/index.md) and executes other agent tools such as/context-recalland/context-save. - Sanitization: There is no explicit requirement for the agent to sanitize or validate external content before updating the context registries.
Audit Metadata