skills/rshade/agent-skills/cost-drift/Gen Agent Trust Hub

cost-drift

Pass

Audited by Gen Agent Trust Hub on Oct 24, 2026

Risk Level: SAFE
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests data from external sources, including JSON output from the finfocus tool and user-defined configuration in .cost-check.yml. While these inputs are entry points for data, the skill's limited capabilities (writing markdown and terminal output) present a negligible attack surface.
  • [COMMAND_EXECUTION]: The skill performs environment checks using 'ls' and 'command -v', and executes 'finfocus' and 'markdownlint'. These shell operations are necessary for its functionality and are targeted at specific, expected utilities.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 24, 2026, 02:18 AM