composio-artifacts

Pass

Audited by Gen Agent Trust Hub on Jun 25, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs the agent to download and install its full implementation from the official ComposioHQ repository on GitHub (ComposioHQ/awesome-claude-skills) using the npx skills add utility.
  • [COMMAND_EXECUTION]: Employs standard shell commands including grep and file existence tests ([ -e ... ]) to detect the skill's current installation status and determine whether it resides in a global or project-specific scope.
  • [PROMPT_INJECTION]: Provides a surface for indirect prompt injection as its primary function is to ingest and process data from external services such as GitHub, Slack, Linear, and Notion (Ingestion points). While the provided stub does not specify boundary markers, sanitization logic, or safety instructions (Boundary markers/Sanitization), the capabilities are restricted to the intended integration tasks (Capability inventory).
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 25, 2026, 06:33 PM
Security Audit — agent-trust-hub — composio-artifacts