codacy-code-review
Pass
Audited by Gen Agent Trust Hub on Apr 1, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTIONCREDENTIALS_UNSAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill executes the official vendor CLI tools
codacyandcodacy-analysisto perform code quality and security checks. Thecodacy-analysistool is specifically directed to analyze the current working tree with potential dependency installation during the process. - [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection (Category 8) when ingesting data from external sources.
- Ingestion points: Fetches pull request titles, descriptions, and content from linked external tickets (Jira, Linear, GitHub Issues) in
SKILL.md. - Boundary markers: There are no explicit delimiters or specific 'ignore' instructions defined for processing this external text.
- Capability inventory: The skill executes shell commands via the Codacy CLI tools for analysis and management.
- Sanitization: No validation or sanitization steps are provided for the content retrieved from external PRs or tickets.
- [CREDENTIALS_UNSAFE]: The documentation identifies
~/.codacy/credentialsas the shared location for CLI authentication. While it mentions the path, it does not instruct the agent to directly access, read, or exfiltrate the contents of this file.
Audit Metadata