personal-finance-coach
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS] (SAFE): The skill installs
numpy,scipy, andpandasvia pip. These are well-established, trusted libraries from the Python Package Index (PyPI) used for numerical calculations and data analysis. - [COMMAND_EXECUTION] (LOW): The skill is authorized to use the
Bashtool. While no specific malicious commands are present in the skill's code, shell access is a high-privilege capability that could be targeted for exploitation. - [PROMPT_INJECTION] (LOW): (Indirect Prompt Injection Surface)
- Ingestion points: The skill ingests untrusted data from the internet via the
mcp__firecrawl__firecrawl_searchandWebFetchtools. - Boundary markers: Absent. There are no specified delimiters or instructions to treat web-fetched content as untrusted data.
- Capability inventory: The skill possesses powerful tools including
Bash,Write, andEdit, which could be abused if the agent executes instructions hidden within retrieved web content. - Sanitization: No sanitization or validation mechanisms are mentioned for the external data processed by the skill.
Audit Metadata