usage-rules
Pass
Audited by Gen Agent Trust Hub on Mar 3, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: Uses the Bash tool to execute mix commands and shell utilities such as mkdir, cp, and rm for package management and file organization.
- [EXTERNAL_DOWNLOADS]: Fetches Elixir package content from the official Hex.pm registry using mix hex.package fetch. This is a standard operation for retrieving package-specific documentation from a well-known service.
- [PROMPT_INJECTION]: Vulnerable to indirect prompt injection through the processing of untrusted usage-rules.md files provided by external packages. * Ingestion points: Reads content from deps//usage-rules.md and .usage-rules/-/usage-rules.md. * Boundary markers: Absent; the skill extracts and presents documentation sections without explicit delimiters or instructions for the agent to ignore embedded commands. * Capability inventory: The skill has access to Bash (command execution), Read (file access), Grep, and Glob. * Sanitization: Absent; there is no validation or filtering of the markdown content retrieved from external packages.
Audit Metadata