golang-samber-oops
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the AI agent on how to capture external data such as HTTP request/response bodies and custom attributes within error objects. This introduces an ingestion surface where untrusted data from external sources could be loaded into the agent's context when it views or processes logs and error reports.
- Ingestion points:
SKILL.mddescribes methods like.Request(req, includeBody),.Response(res, includeBody), and.With(key, value)for attaching arbitrary data to errors. - Boundary markers: The instructions do not explicitly suggest using delimiters or escape characters when the agent processes these captured values, although the library's design naturally separates technical attributes from the error message.
- Capability inventory: The agent has access to file system modification and shell execution tools (
Write,Edit,Bash) which could be targeted by sophisticated injections, though the risk here is low and inherent to the task of error analysis. - Sanitization: The skill advocates for the use of
.Public()to define user-safe messages, which effectively separates technical (and potentially untrusted) data from user-facing output.
Audit Metadata