generate-slsa
Pass
Audited by Gen Agent Trust Hub on Oct 24, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill operates by fetching and analyzing existing pipeline configurations to guide the user through placement and setup. This processing of untrusted external data creates a surface for indirect prompt injection attacks.\n
- Ingestion points: Pipeline definitions are retrieved using the
harness_gettool during the initial phases of the interaction wizard (SKILL.md).\n - Boundary markers: The skill's instructions lack explicit markers or protective prompts to prevent the agent from following instructions potentially embedded within the fetched YAML data.\n
- Capability inventory: The skill possesses the ability to modify pipeline configurations via the
harness_updatetool and can query project and organizational metadata (SKILL.md).\n - Sanitization: There are no verification or sanitization steps specified for the external pipeline content before it is processed by the agent.
Audit Metadata