exec-quality-narrative
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external data such as quality digests, portfolio roll-ups, DORA metrics, and OKR grading to generate narratives. This creates a surface for indirect prompt injection if inputs contain instructions designed to influence the agent.\n
- Ingestion points: Quality digests, Portfolio roll-ups, DORA delivery metrics, and OKR grading artifacts in SKILL.md.\n
- Boundary markers: The instructions lack specific delimiters or instructions to ignore embedded commands in the processed data.\n
- Capability inventory: The skill is restricted to narrative generation and does not have file-system, network, or command execution capabilities.\n
- Sanitization: No sanitization or escaping mechanisms are specified for the external data inputs.\n- [EXTERNAL_DOWNLOADS]: The skill references external documentation and definitions from DORA (dora.dev) and Wikipedia to maintain terminology precision.
Audit Metadata