data-processing
Pass
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONDATA_EXFILTRATION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes structured data from external files (JSON, YAML, TOML) using the Bash tool, creating a surface for indirect prompt injection if the files contain malicious instructions.
- Ingestion points: File-reading operations using jq and yq in SKILL.md, references/jq-patterns.md, and references/yq-patterns.md.
- Boundary markers: Absent; the skill does not define delimiters or instructions to ignore embedded commands in the processed data.
- Capability inventory: Access to the Bash tool for command execution and file modification (e.g., yq -i).
- Sanitization: No evidence of input validation, escaping, or filtering for data passed to shell commands.
- [COMMAND_EXECUTION]: The skill extensively uses the Bash tool to run jq and yq commands, including complex patterns like shell loops and variable capture (e.g., VERSION=$(jq -r '.version' package.json)).
- [DATA_EXFILTRATION]: The skill provides patterns to access and query configuration files that frequently contain sensitive data, such as environment variables in Docker Compose files and GitHub Actions workflow configurations (.github/workflows/ci.yml).
Audit Metadata