skills/clawlink-hq/skills/blackbaud/Gen Agent Trust Hub

blackbaud

Pass

Audited by Gen Agent Trust Hub on Jun 28, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill uses npx to download and run the @useclawlink/cli package from the NPM registry. This package is the official tool from the skill's authoring organization.\n- [COMMAND_EXECUTION]: Interaction with Blackbaud is handled via shell commands (npx @useclawlink/cli ...) in SKILL.md, allowing the agent to find actions, describe inputs, and execute operations.\n- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface because it processes data retrieved from an external service (Blackbaud).\n
  • Ingestion points: Data from the external CRM enters the agent's context through the output of CLI actions and run commands defined in SKILL.md.\n
  • Boundary markers: No explicit delimiters or instructions are provided to the agent to distinguish between its instructions and the data fetched from the external source.\n
  • Capability inventory: The skill allows the agent to execute subprocess commands (via npx) in SKILL.md to perform read and write operations on the external service.\n
  • Sanitization: The instructions do not specify any validation or sanitization of the data retrieved from the external source before it is processed.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 28, 2026, 02:42 PM
Security Audit — agent-trust-hub — blackbaud