helpmetest-discover
Pass
Audited by Gen Agent Trust Hub on Mar 9, 2026
Risk Level: SAFECREDENTIALS_UNSAFEPROMPT_INJECTION
Full Analysis
- [CREDENTIALS_UNSAFE]: The skill includes a hardcoded default password ('SecureTest123!') in the template for creating Persona artifacts in SKILL.md. While intended for test environments, hardcoding credentials is a security anti-pattern.- [PROMPT_INJECTION]: The skill is vulnerable to Indirect Prompt Injection (Category 8). It navigates to external URLs and reads page content to determine business logic and features without explicit sanitization or boundary markers to ignore instructions embedded in the target website's content.
- Ingestion points: External website content via 'helpmetest_run_interactive_command' in SKILL.md.
- Boundary markers: Absent. Instructions do not specify ignoring instructions found on the page.
- Capability inventory: 'helpmetest_run_interactive_command' (navigation/interaction), 'helpmetest_upsert_artifact' (data storage) in SKILL.md.
- Sanitization: Absent. External content is used directly to build Feature and Persona artifacts.
Audit Metadata