skills/mukul975/anthropic-cybersecurity-skills/performing-open-source-intelligence-gathering/Gen Agent Trust Hub
performing-open-source-intelligence-gathering
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill's automation scripts ingest untrusted data from external web sources.
- Ingestion points:
scripts/process.py(lines 155, 169, 187) andscripts/agent.py(line 89) fetch HTML and text content from target domains. - Boundary markers: Absent. The scripts do not use delimiters or instructions to ignore embedded commands in the fetched content.
- Capability inventory: The scripts perform network requests (
requests.get) and write report files to the local filesystem (scripts/process.pylines 258-356). - Sanitization: Absent. Content is parsed for emails or technology signatures but is otherwise processed as raw strings.
- [EXTERNAL_DOWNLOADS]: The Python scripts perform numerous network operations to gather data from external services.
- Evidence:
scripts/agent.pyqueriesapi.hunter.ioandgoogle.com.scripts/process.pyqueriescrt.shand the target domain directly.
Audit Metadata