check-identity-pack

Pass

Audited by Gen Agent Trust Hub on Oct 15, 2026

Risk Level: SAFEDATA_EXFILTRATIONINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [DATA_EXFILTRATION]: The skill is designed to transmit highly sensitive identity documents—including passports, driver's licenses, and bank statements—to an external endpoint (https://www.stipple.sh/v1/identity-check).
  • Evidence: Step 3 of the instructions uses a curl command to POST multipart files to a non-whitelisted domain.
  • [EXTERNAL_DOWNLOADS]: The skill directs users to an external website (stipple.sh) to register for API keys and access documentation.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted document content, which could potentially contain malicious instructions intended to manipulate the agent's output or reporting.
  • Ingestion points: User-provided document files and URLs (e.g., passport.pdf, bank-statement.pdf) as described in SKILL.md.
  • Boundary markers: Absent. The skill lacks explicit instructions or delimiters to isolate document content from the agent's command logic.
  • Capability inventory: The agent has the capability to perform network operations (curl) and process file data.
  • Sanitization: Absent. The skill does not include steps to sanitize or validate the content of the documents before they are analyzed or transmitted.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 15, 2026, 04:40 AM