python-pro
Fail
Audited by Gen Agent Trust Hub on Sep 5, 2026
Risk Level: CRITICALEXTERNAL_DOWNLOADSMETADATA_POISONINGINDIRECT_PROMPT_INJECTION
Full Analysis
- [METADATA_POISONING]: The skill file
SKILL.mdhas been flagged by automated reputation scanners as malicious (FileRepMalware). - [EXTERNAL_DOWNLOADS]: The skill references an external documentation URL (
https://jeffallan.github.io/claude-skills/skills/language/python-pro/) that is blacklisted by URL reputation services. - [INDIRECT_PROMPT_INJECTION]: The skill creates a vulnerability surface for indirect prompt injection by instructing the agent to ingest and process codebase content through powerful validation and testing tools without defining security boundaries or sanitization protocols.
- Ingestion points: Codebase files and dependencies reviewed during the core workflow (defined in
SKILL.md). - Boundary markers: The instructions lack delimiters or warnings to ignore malicious instructions embedded in the processed data.
- Capability inventory: The skill utilizes subprocess executions for
mypy,black,ruff,pytest,poetry,pip, andtwine(found inSKILL.mdandreferences/packaging.md). - Sanitization: No mechanisms for escaping or filtering untrusted content before tool invocation are present.
Recommendations
- CRITICAL: 1 file(s) identified as malware by FileRep - DO NOT USE
- AI detected serious security threats
- Contains 2 malicious URL(s) - DO NOT USE
Audit Metadata