check-demo-analytics
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes
curlcommands to interact with internal and production GraphQL endpoints. These operations are required for the skill's stated purpose of cross-referencing analytics with sales pipeline data. - [INDIRECT_PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it processes and summarizes data from external sources (CRM and Ackee) which could contain malicious payloads.
- Ingestion points: Data is ingested from the Ackee API (
$ACKEE_DOMAIN/api) and the CRM GraphQL endpoint (https://crm.psquared.dev/graphql) in SKILL.md. - Boundary markers: The skill uses markdown headers and box-drawing characters in the report, but does not provide specific instructions to the agent to treat data from these tools as untrusted or to ignore embedded instructions.
- Capability inventory: The skill utilizes
curlfor all network communications and reads local environment files (.env). - Sanitization: There is no evidence of string sanitization or filtering for the data retrieved from external APIs before it is interpolated into the final report.
Audit Metadata