configure-dast-scan
Pass
Audited by Gen Agent Trust Hub on Oct 24, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill analyzes existing Harness pipeline YAML to identify stages and insertion points, which creates an indirect prompt injection surface where malicious instructions embedded in the pipeline could influence agent behavior.
- Ingestion points: The skill retrieves pipeline configurations from the platform using the
harness_gettool in Step 1. - Boundary markers: There are no explicit instructions or delimiters used to separate the ingested pipeline YAML from the agent's core instruction set.
- Capability inventory: The skill has the capability to modify and update pipeline definitions through the
harness_updatetool and provides templates for network-activecurlcommands. - Sanitization: The skill does not specify sanitization or schema validation steps for the YAML content before processing it for modification.
Audit Metadata