create-sbom
Pass
Audited by Gen Agent Trust Hub on Oct 24, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests external, potentially untrusted data by fetching existing pipeline configurations via the harness_get tool. This data is used to populate an interactive wizard and generate a new pipeline YAML string for updates. A malicious pipeline configuration could potentially contain embedded instructions aimed at influencing the agent's behavior during the setup process.
- Ingestion points: Existing pipeline YAML fetched via harness_get in SKILL.md (Phase 1).
- Boundary markers: The skill does not define specific delimiters or instructions for the agent to ignore embedded commands within the fetched YAML.
- Capability inventory: The skill possesses the harness_update capability, allowing it to modify pipeline configurations across CI, CD, and Security stages.
- Sanitization: No explicit sanitization or validation of the fetched pipeline content is described before it is used to drive the wizard's logic.
Audit Metadata