analyze-repo
Pass
Audited by Gen Agent Trust Hub on Aug 10, 2026
Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it processes untrusted repository data and embeds it into an HTML report without explicit sanitization.
- Ingestion points: The Explore subagent is instructed to map the entire codebase, reading files, dependencies, and patterns across the repository.
- Boundary markers: Absent; there are no instructions to use delimiters or ignore embedded instructions within the analyzed repository data.
- Capability inventory: The skill has the capability to write files to the temporary directory and execute the
opencommand to launch a browser. - Sanitization: Absent; the instructions for Step 2 and the template in
references/html-report-template.mdrely on direct variable replacement without mention of escaping or filtering. - [EXTERNAL_DOWNLOADS]: The generated report fetches the Tailwind CSS framework and the Mermaid.js library from well-known content delivery networks (Tailwind and jsDelivr).
- [COMMAND_EXECUTION]: The skill uses shell commands to determine a temporary report path and executes the
opencommand to display the generated HTML report to the user.
Audit Metadata