ss-build
Pass
Audited by Gen Agent Trust Hub on Sep 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill relies on data ingested from registry files such as .styleseed/project.json and artifact bundles in .styleseed/bundles/ to determine the build context and rules. If these files are modified by an external actor, they could potentially influence the agent's behavior during the build cycle.
- Ingestion points: The skill reads .styleseed/project.json, .styleseed/artifacts/index.json, and bundle/manifest files in Step 1.
- Boundary markers: There are no explicit instructions to use delimiters or ignore instructions embedded within these files.
- Capability inventory: The skill is authorized to use tools including Bash, Write, Edit, and WebFetch.
- Sanitization: The instructions do not define any sanitization or validation protocols for the content read from these local files.
Audit Metadata