oss-review
Pass
Audited by Gen Agent Trust Hub on Jul 12, 2026
Risk Level: SAFEPROMPT_INJECTIONDATA_EXFILTRATION
Full Analysis
- [DATA_EXFILTRATION]: The skill is configured to read from and write to specific local file system paths outside the immediate project root (e.g.,
~/.claude/plugins/config/claude-for-legal/ip-legal/CLAUDE.mdand related matter subdirectories). This behavior is intended for managing persistent legal 'practice profiles' and 'matter workspaces' within a specific plugin environment. Users should ensure the security and integrity of these configuration directories. - [PROMPT_INJECTION]: The skill possesses a surface for Indirect Prompt Injection as it is designed to ingest and process untrusted external data from dependency manifests (package.json, requirements.txt, SBOMs) and code repositories. There is a risk that a maliciously crafted manifest file could contain instructions designed to influence the agent's behavior during the audit process.
- Ingestion points: Project manifest files (package.json, requirements.txt, go.mod, etc.) and SBOM files (SPDX/CycloneDX) provided by the user.
- Boundary markers: None identified. The instructions do not specify the use of clear delimiters or 'ignore' warnings for the data being processed.
- Capability inventory: The skill is authorized to read local configuration files, read user-provided project files, and write output to the designated matter workspace folders.
- Sanitization: No explicit sanitization or validation of the content within the ingested manifest files is described in the workflow.
Audit Metadata