qcsd-cicd-swarm
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external pipeline artifacts and test results (PIPELINE_ARTIFACTS), which are untrusted data sources. Malicious instructions embedded in these artifacts could potentially influence the behavior of the orchestrator or its sub-agents. * Ingestion points: PIPELINE_ARTIFACTS path defined in SKILL.md and processed in steps/01-flag-detection.md. * Boundary markers: The instructions do not define clear delimiters or 'ignore' markers for data read from the pipeline artifacts. * Capability inventory: The skill has the ability to spawn sub-agents, write report files to the OUTPUT_FOLDER, and execute shell commands using the aqe utility for memory storage and retrieval. * Sanitization: No explicit sanitization or validation of the content within the pipeline artifacts is mentioned before the data is used in decision-making logic or passed to other agents.
Audit Metadata