quality-assurance-auditor
Pass
Audited by Gen Agent Trust Hub on Sep 3, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection as its core function requires parsing diverse, untrusted data generated in the project workspace to make auditing decisions.\n
- Ingestion points: The skill reads content from multiple directories, including
workspace/problem/,methods/,results/,paper/, andcode/. These files (markdown, JSON, and source code) could contain malicious instructions designed to influence the auditor's verdict.\n - Boundary markers: Absent. The instructions do not define delimiters or specific 'ignore embedded instructions' warnings for the artifact content it processes.\n
- Capability inventory: The skill has significant influence over the agent's workflow, as it determines the
final_assembly_allowedstatus and directs handoffs to upstream skills likepython-model-code-generatororworkflow-orchestrator.\n - Sanitization: Absent. There is no evidence of validation or sanitization routines for the content of the files it ingests.\n- [NO_CODE]: The skill consists entirely of markdown-based instructions and metadata; it does not include or execute any standalone scripts or binary files.
Audit Metadata