skills/ryoppippi/ccusage/rust/Gen Agent Trust Hub

rust

Pass

Audited by Gen Agent Trust Hub on Jul 10, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill specifies that the build.rs script fetches pinned pricing JSON from the LiteLLM repository during the build process, which is a well-known and standard source for model pricing data.
  • [COMMAND_EXECUTION]: The instructions include example shell commands using fd and sed for repository exploration and reading adapter documentation.
  • [PROMPT_INJECTION]: An indirect prompt injection surface is present as the skill directs the agent to ingest content from local documentation files. 1. Ingestion points: rust/crates/ccusage/src/adapter/<agent>/README.md (via sed). 2. Boundary markers: Absent. 3. Capability inventory: Shell command execution (fd, sed, cargo test). 4. Sanitization: Not specified.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 10, 2026, 07:21 AM
Security Audit — agent-trust-hub — rust