keenable

Pass

Audited by Gen Agent Trust Hub on Oct 26, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The scripts/keenable_setup.py script uses subprocess.run to execute the claude mcp add command, which configures the Keenable MCP server within the Claude environment. The command is implemented by passing an argument list rather than a shell string, mitigating risks of shell injection during the setup process.
  • [INDIRECT_PROMPT_INJECTION]: The skill retrieves and processes data from external web sources, which serves as a vector for indirect prompt injection if those sources contain malicious instructions.
  • Ingestion points: External content enters the agent's context via the search snippets in scripts/keenable_search.py and full page markdown in scripts/keenable_fetch.py.
  • Boundary markers: The scripts use markdown headers and visual separators (e.g., horizontal lines) to structure results, but they do not provide explicit instructions to the agent to treat the fetched content as untrusted data.
  • Capability inventory: The skill has the capability to perform network requests to the vendor's API and execute setup commands via the Claude CLI.
  • Sanitization: Fetched content is displayed as-is without sanitization or filtering for potential prompt injection patterns.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 26, 2026, 06:34 PM