audit-full
Pass
Audited by Gen Agent Trust Hub on Feb 27, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the Bash tool to execute a bundled script (estimate-tokens.sh) and recommends standard ecosystem audit tools such as npm audit, pip-audit, and license-checker. These executions are consistent with the skill's purpose and are performed with user-controlled parameters.- [INDIRECT_PROMPT_INJECTION]: The skill possesses a vulnerability surface for indirect prompt injection as it processes large amounts of untrusted codebase data through Read and Grep tools while having access to the Bash tool. The workflow includes user interaction steps which act as a manual verification gate.
- Ingestion points: Codebase files loaded into context via Glob and Read tools (SKILL.md, Step 2).
- Boundary markers: No explicit instructions or delimiters are used to warn the agent about ignoring instructions embedded within the audited code.
- Capability inventory: Access to Bash, TaskCreate, Read, Grep, and Glob tools.
- Sanitization: No sanitization of the ingested code content is performed before processing.- [EXTERNAL_DOWNLOADS]: The documentation suggests the use of standard auditing tools from well-known registries like NPM and PyPI, which are recognized as safe sources.
Audit Metadata