license-checker
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from package.json and license files located in the node_modules directory, which could contain malicious instructions designed to manipulate LLM behavior. \n
- Ingestion points: Reads metadata and file snippets from third-party packages in node_modules (SKILL.md). \n
- Boundary markers: Employs a specific prompt template in Step 2 to constrain LLM output to SPDX IDs. \n
- Capability inventory: Utilizes bash shell commands, including find, jq, and grep, to process local file system data. \n
- Sanitization: No explicit sanitization or filtering of the content extracted from the files is performed before it is processed. \n- [COMMAND_EXECUTION]: The skill executes shell commands (find, jq, grep, printf) within a bash script to iterate through and parse package metadata. The script correctly quotes variables to prevent command injection from malicious file paths or metadata fields.
Audit Metadata