sota-ruby
Pass
Audited by Gen Agent Trust Hub on Nov 6, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill's primary function is to audit external Ruby repositories, which creates a surface for indirect prompt injection. Malicious instructions could be embedded within the source code, Gemfiles, or configuration files that the agent is instructed to analyze.
- Ingestion points: The agent ingests data from Ruby source files,
Gemfile,Gemfile.lock, and linter configurations (e.g.,.rubocop.yml) when operating inAUDIT modeas described inSKILL.mdand therules/directory. - Boundary markers: The skill does not provide specific instructions to use delimiters or "ignore previous instructions" markers when reading and processing external code content.
- Capability inventory: The skill enables the agent to read arbitrary files within a project and suggests the use of tools such as
grep,rubocop, andbrakemanto process this data. - Sanitization: There are no instructions for the agent to sanitize or escape the content of audited files before they are brought into the LLM context for evaluation.
Audit Metadata