api-security-tester

Pass

Audited by Gen Agent Trust Hub on Aug 8, 2026

Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
  • [NO_CODE]: The skill contains only markdown instructions and configuration metadata. There are no scripts, binaries, or automated installation processes included in the package.
  • [PROMPT_INJECTION]: The skill instructs the agent to analyze external, untrusted API endpoints and documentation, which introduces a surface for indirect prompt injection where an attacker-controlled API could influence agent behavior.
  • Ingestion points: The instructions specify testing for "REST endpoints", "GraphQL APIs", "WebSocket APIs", and "API docs" (SKILL.md).
  • Boundary markers: The skill does not provide instructions to use delimiters or to ignore instructions embedded within the data retrieved from external sources.
  • Capability inventory: The skill configuration enables the use of codebase and filesystem tools.
  • Sanitization: No explicit sanitization, filtering, or validation steps are defined for processing external network data.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 8, 2026, 11:03 AM
Security Audit — agent-trust-hub — api-security-tester