Changelog Curator
Warn
Audited by Snyk on Mar 29, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.80). The skill's SKILL.md explicitly instructs the agent to ingest and parse user-provided git logs or lists of PR titles/descriptions ("Provide: The git log ... or a list of PRs" and "Step 1 — Parse the input"), which are untrusted, user-generated third-party content and are used to drive categorization and changelog generation, so malicious text in those inputs could influence the agent's behavior.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata