cve-risk-score
Pass
Audited by Gen Agent Trust Hub on Apr 20, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill's workflow requires the agent to execute a local Python script (
tools/nvd-lookup.py) to process CVE lookups. - Evidence: SKILL.md specifies the command
python3 tools/nvd-lookup.py CVE-XXXX-XXXXXfor data retrieval. - [EXTERNAL_DOWNLOADS]: The skill connects to the NVD API to fetch vulnerability data. While NIST is a well-known government service, this represents an external network dependency.
- Evidence: reference/nvd-api-reference.md defines the endpoint
https://services.nvd.nist.gov/rest/json/cves/2.0. - [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests untrusted data (CVE descriptions and metadata) from an external API and presents it to the agent.
- Ingestion points: Vulnerability descriptions, CWE labels, and reference URLs from the NVD API response.
- Boundary markers: Absent; the skill does not specify delimiters or instructions to ignore embedded content in the fetched data.
- Capability inventory: The agent has shell access to execute the
nvd-lookup.pyscript. - Sanitization: No validation or sanitization of the remote API content is described in the skill instructions.
Audit Metadata