swcr-register

Pass

Audited by Gen Agent Trust Hub on Jul 1, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill performs 'git clone' operations to download source code from external GitHub URLs provided by the user.
  • [COMMAND_EXECUTION]: The skill executes local Python scripts and shell commands to perform file system scanning, line counting, and DOCX document generation.
  • [PROMPT_INJECTION]: The skill is vulnerable to Indirect Prompt Injection (Category 8).
  • Ingestion points: The scripts 'generate_form_info.py' and 'generate_manual.py' parse untrusted text content from README files and source code repositories provided by the user.
  • Boundary markers: There are no delimiters or explicit instructions to the agent to treat the ingested project data as untrusted data rather than executable instructions.
  • Capability inventory: The skill has capabilities for file system read/write, shell command execution, and automated web form filling via external skill dependencies.
  • Sanitization: Features and descriptions are extracted from project files and used to populate registration metadata without sanitization, allowing malicious project content to potentially influence agent behavior during the 'web-form-fill' stage.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 1, 2026, 12:21 PM
Security Audit — agent-trust-hub — swcr-register