clawdtm-review
Pass
Audited by Gen Agent Trust Hub on Feb 19, 2026
Risk Level: SAFEDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
- Data Exposure & Exfiltration (LOW): The skill performs network operations using
curlto the external domainclawdtm.com. While this is the primary purpose of the skill, the domain is not on the established trusted list. - Evidence: Multiple
curlcommands targetinghttps://clawdtm.com/api/v1/. - Indirect Prompt Injection (LOW): The skill possesses a surface for indirect prompt injection as it retrieves and processes
review_textfrom an external API, which could contain instructions intended to influence the agent's behavior. - Ingestion points: API responses from
https://clawdtm.com/api/v1/skills/reviewsinSKILL.md. - Boundary markers: Absent; no instructions are provided to the agent to treat external review content as untrusted data.
- Capability inventory: The agent can perform network requests (
curl) and modify its own data on the remote platform. - Sanitization: Absent; the skill does not specify any validation or filtering of the retrieved review text.
Audit Metadata