reticulum-go
Pass
Audited by Gen Agent Trust Hub on Sep 10, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill fetches content from the external domain
reticulum-go.quad4.ioand processes it via tools likefetch_page,get_topic, andsearch_docs. This creates an attack surface where instructions embedded in the documentation could influence the agent. - Ingestion points: Data is ingested through the retrieval tools defined in
references/tools.md. - Boundary markers: There are no explicit instructions or delimiters used to separate documentation content from agent instructions.
- Capability inventory: The skill allows the agent to read, search, and navigate sections of external web content.
- Sanitization: The skill does not implement validation or sanitization of the fetched documentation text.
- [EXTERNAL_DOWNLOADS]: The skill performs runtime network requests to fetch documentation from the author-controlled domain
reticulum-go.quad4.io. - [COMMAND_EXECUTION]: The
SKILL.mdfile instructs the user to execute shell commands (go test ./... && go build) to build the skill binary.
Audit Metadata