codacy
Pass
Audited by Gen Agent Trust Hub on Mar 12, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill requires the @membranehq/cli package to be installed globally via npm. This is a vendor-provided tool necessary for the integration's functionality and is considered a safe resource within the scope of the vendor's own infrastructure.\n- [COMMAND_EXECUTION]: The skill uses the membrane CLI to manage authentication connections and execute various actions on the Codacy platform, such as searching for actions and running proxied API requests.\n- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection by processing external data fetched from Codacy. Ingestion points: Commit analysis, pull request issues, and repository metadata (SKILL.md). Boundary markers: The skill instructions do not define delimiters or instructions to ignore embedded commands within the fetched data. Capability inventory: The agent can execute system actions and perform network requests via the membrane tool (SKILL.md). Sanitization: There are no explicit instructions for sanitizing or escaping the content retrieved from the external platform before processing.
Audit Metadata