find-docs
Pass
Audited by Gen Agent Trust Hub on Jul 2, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill requires downloading and installing or running an external package ctx7 from the NPM registry using
npm install -g ctx7@latestornpx ctx7@latest.- [COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands using the ctx7 CLI, specificallyctx7 library,ctx7 docs, andctx7 loginto perform its primary function of retrieving documentation.- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it processes external content (documentation and code snippets) retrieved via the ctx7 tool. - Ingestion points: Data returned by the
ctx7 docscommand execution is ingested into the agent's context. - Boundary markers: The skill instructions do not specify any markers or delimiters to wrap the external documentation content, which could allow malicious instructions in the docs to be mistaken for agent instructions.
- Capability inventory: The skill has access to shell execution (
npm,npx,ctx7) and environment variable management. - Sanitization: There is no evidence of sanitization or filtering of the content retrieved from the external documentation service before it is presented to the agent.
Audit Metadata