performance-budgeting
Pass
Audited by Gen Agent Trust Hub on Sep 22, 2026
Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTION
Full Analysis
- [NO_CODE]: The skill consists entirely of markdown instructions without any associated scripts or tool configurations.
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to request and process user-supplied performance data and CI/CD configurations. While these inputs could potentially contain malicious content, the skill does not possess any tools or executable code to act on such instructions.
- Ingestion points: User-provided metrics, journeys, and CI/CD info in SKILL.md.
- Boundary markers: Absent.
- Capability inventory: None. The skill defines no scripts or tool usage.
- Sanitization: Absent.
Audit Metadata