plan-campaign
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFE
Full Analysis
- [DATA_EXPOSURE]: The skill reads the
PSQUARED_CRM_TOKENfrom a local.envfile. This is a standard and recommended practice for secret management, avoiding hardcoded credentials within the script or instructions. - [COMMAND_EXECUTION]: The skill utilizes
curlto interact with a GraphQL API athttps://crm.psquared.dev/graphql. These operations are limited to standard API queries and mutations (fetching opportunities, creating campaigns, and updating records) consistent with the skill's stated purpose. - [INDIRECT_PROMPT_INJECTION]: The skill has a surface for indirect prompt injection as it processes data retrieved from the CRM (e.g., company names).
- Ingestion points: CRM opportunity data retrieved in STEP 1.
- Boundary markers: None explicitly defined for the external data processing.
- Capability inventory: Network operations via
curlto update CRM records. - Sanitization: No specific sanitization logic is mentioned for the data returned from the CRM, though the data is primarily used for filtering and display.
Audit Metadata