manage-openapi-overlays

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFE
Full Analysis
  • [PROMPT_INJECTION] (SAFE): No instructions attempting to override agent behavior or bypass safety filters were detected.
  • [CREDENTIALS_UNSAFE] (SAFE): No hardcoded credentials found. The skill correctly uses environment variables and placeholders (e.g., API_KEY, MYAPI_ACCESS_KEY) for authentication and explicitly warns against insecure practices like query-parameter authentication.
  • [COMMAND_EXECUTION] (SAFE): Commands mentioned (speakeasy, yq, jq) are standard developer tools for OpenAPI validation and JSON/YAML processing. No high-risk command execution or privilege escalation was found.
  • [DATA_EXFILTRATION] (SAFE): No patterns for unauthorized data access or external transmission of sensitive information were identified.
  • [REMOTE_CODE_EXECUTION] (SAFE): No remote script execution or dynamic code generation from untrusted sources was detected.
  • [INDIRECT_PROMPT_INJECTION] (SAFE): While the skill ingests external specification files (spec.yaml, spec.json) in content/validation.md, it does so using structured querying tools (yq, jq) and a specialized validator (speakeasy). There is no evidence of unsafe prompt interpolation or execution paths for untrusted data.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:07 PM