crw-extract
Pass
Audited by Gen Agent Trust Hub on Jun 18, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes untrusted data from external websites, which represents a surface for indirect prompt injection.
- Ingestion points: External web content is retrieved through
crw scrapeandcrw_scrapecommands as described in SKILL.md. - Boundary markers: The instructions do not define explicit boundary markers or provide warnings to the agent to ignore instructions embedded within the retrieved web content.
- Capability inventory: The skill utilizes
Bash(crw:*),Bash(curl:*), andReadtools, enabling it to execute local CLI commands and read local files (SKILL.md). - Sanitization: No explicit sanitization, filtering, or validation of the retrieved web content is documented before the data is processed by the agent.
Audit Metadata