factory-init
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process untrusted data from existing (brownfield) repositories during the bootstrap and refresh routes.
- Ingestion points: The skill reads decision records from
.adlc/memory/, compiled artifacts likePRD.mdandAD.md, and scans the general codebase to build a coverage matrix. - Boundary markers: There are no explicit instructions or delimiters defined to prevent the agent from following potential instructions embedded within the codebase or documentation being analyzed.
- Capability inventory: The skill possesses the ability to orchestrate a sequence of other skills and write findings to the local filesystem in the
.adlc/directory. - Sanitization: The instructions do not specify any validation or sanitization steps for the repository content before it is processed by the agent during the sweep step.
Audit Metadata