heyeddi-ci-config
Warn
Audited by Snyk on Aug 11, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.30). At runtime the agent ingests free text/JSON returned by
load_policy_contractfrom the production contract feed URLhttps://cihook.heyeddi.com/api/public/eddi-ci-policy(and can fall back to human docs page text), which is not first-party provider content that can be assumed trusted against outsider submission.
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (high risk: 1.00). The skill's load_policy_contract script fetches the living contract at runtime from https://cihook.heyeddi.com/api/public/eddi-ci-policy and the returned knobs/guide/minimal_example are treated as authoritative inputs for generating prompts and the eddi-ci.yaml, so this external URL directly controls agent instructions.
Issues (2)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
W012
MEDIUMUnverifiable external dependency detected (runtime URL that controls agent).
Audit Metadata