oulang-knowledge-capture
Fail
Audited by Snyk on Apr 12, 2026
Risk Level: HIGH
Full Analysis
HIGH W007: Insecure credential handling detected in skill instructions.
- Insecure credential handling detected (high risk: 1.00). The skill explicitly instructs extracting and writing "Credentials, payment accounts" and "VERBATIM" stakeholder quotes from the conversation into Notion pages, which requires the LLM to include secret values verbatim in its outputs (high exfiltration risk).
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (high risk: 0.80). This skill issues runtime Notion fetches (e.g., notion-fetch of topic pages and the Runs collection such as collection://e1130bc0-477d-48dd-81e1-5a420f8b9180 and page IDs like 3402ea9b77ad81b5aefaf0e86e954ab3) and explicitly reads that remote page content to decide what to write or whether to act, so the fetched external content can directly control agent behavior.
Issues (2)
W007
HIGHInsecure credential handling detected in skill instructions.
W012
MEDIUMUnverifiable external dependency detected (runtime URL that controls agent).
Audit Metadata