tester-mindset
Pass
Audited by Gen Agent Trust Hub on Sep 25, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to analyze untrusted data including user-provided code, plans, and claims, creating a potential surface for indirect prompt injection.
- Ingestion points: The skill ingests external content to identify edge cases, failure modes, and acceptance criteria as described in
SKILL.md. - Boundary markers: There are no explicit instructions to use delimiters or ignore instructions embedded within the data being tested.
- Capability inventory: The skill specifies the ability to run "authorized, bounded probes" and design test strategies, which involve interacting with the system under test.
- Sanitization: No methods for escaping or validating the content of the claims being tested are defined.
Audit Metadata