Layer 2s
Pass
Audited by Gen Agent Trust Hub on Nov 1, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill's
install.commandandsetupinstructions utilizecurlto fetch content fromhttps://ethskills.com/l2s/SKILL.mdand suggest installing plugins fromhttps://github.com/austintgriffith/ethskillsandclawhub. These sources are outside the verified vendor infrastructure. - [INDIRECT_PROMPT_INJECTION]: The skill implements a pattern where untrusted data enters the agent context.
- Ingestion points: External content is fetched via
curlfromethskills.comas defined incatalog.json. - Boundary markers: None identified in the provided files to delimit the external content from system instructions.
- Capability inventory: The skill facilitates the installation of external plugins and tools via
claude plugin installandclawhub install. - Sanitization: There is no evidence of sanitization or filtering of the content fetched from the remote URL before it is processed by the agent.
Audit Metadata