golang-samber-oops

Pass

Audited by Gen Agent Trust Hub on Sep 14, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill operates on Go source code, which can be used as a vector for indirect prompt injection if malicious instructions are embedded in files processed by the agent.
  • Ingestion points: The agent reads project files (**/*.go) as defined in SKILL.md using tools like Read, Glob, Grep, and LSP. WebFetch also allows ingestion of remote data.
  • Boundary markers: There are no instructions in SKILL.md or references/advanced.md to separate the agent's instructions from the content of the data files it reads.
  • Capability inventory: As per SKILL.md, the agent can perform file writes/edits and execute shell commands via restricted tools (go, git, gopls).
  • Sanitization: The skill does not define any sanitization or validation logic for data ingested from the project environment.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 14, 2026, 05:10 AM
Security Audit — agent-trust-hub — golang-samber-oops