change-scope
Pass
Audited by Gen Agent Trust Hub on Nov 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill's primary function involves ingesting and processing untrusted data from user requests and external project documents to update authoritative contracts.
- Ingestion points: The skill reads 'the user's requested change', 'owning requirement', 'full spec', 'relevant ADRs', and 'accepted design or prototype decisions' as specified in
SKILL.md. - Boundary markers: Absent; there are no instructions provided to the agent to use delimiters or to disregard potentially malicious instructions embedded within the ingested documents.
- Capability inventory: The skill is authorized to modify repository documents, including requirements, specifications, and task plans. It is explicitly restricted from modifying production code, tests, or runtime configurations (
SKILL.md). - Sanitization: Absent; no validation, escaping, or filtering of the external content is mentioned before it is processed and used to update documents.
Audit Metadata