outlit
Pass
Audited by Gen Agent Trust Hub on Jun 23, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill uses a set of registered tools (
outlit_*) to interface with an external API. These tools are scoped to customer intelligence tasks like retrieving timelines, facts, and customer records. - [SAFE]: The SQL functionality is restricted to
SELECTqueries as outlined in the documentation, with explicit instructions to useLIMITand standard schema inspection viaoutlit_schemabefore execution. - [SAFE]: The skill implements good practices for secret management by instructing the user to set the
OUTLIT_API_KEYenvironment variable if it is missing, rather than hardcoding credentials. - [SAFE]: The prompt injection detection hint regarding concealment was determined to be a false positive; the instructions merely guide the agent to provide concise, evidence-backed answers and handle missing data transparently rather than hiding malicious actions from the user.
Audit Metadata