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

recallai

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 fetch and execute the @useclawlink/cli package from the NPM registry.
  • [COMMAND_EXECUTION]: Uses CLI commands to perform operations such as creating meeting bots, managing Google/Zoom logins, and synchronizing calendars.
  • [COMMAND_EXECUTION]: Manages authentication tokens by reading and writing to the local file ~/.clawlink/credentials.json.
  • [PROMPT_INJECTION]: The skill processes user-supplied data for searching actions and constructing JSON payloads for API execution, presenting an indirect prompt injection surface.
  • Ingestion points: User input in npx @useclawlink/cli actions recallai "<what you want to do>" and the --input flag in the run command.
  • Boundary markers: No explicit delimiters or instructions to ignore embedded commands are present in the skill.
  • Capability inventory: Includes creating/deleting bots, managing calendar integrations, and generating authentication tokens via network-connected CLI tools.
  • Sanitization: No sanitization or validation of external input is specified in the skill instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 28, 2026, 02:43 PM
Security Audit — agent-trust-hub — recallai