archive-project

Pass

Audited by Gen Agent Trust Hub on Mar 5, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses the Bash tool to perform file system operations (mkdir, mv). While the project name is quoted in the command, there is a lack of explicit validation of the project name variable, which could theoretically allow for directory traversal depending on the agent's environment.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it reads and processes the content of 'STATUS.md' files within project directories to 'understand current state'.
  • Ingestion points: 'projects/$PROJECT_NAME/STATUS.md'.
  • Boundary markers: None identified; the file content is read directly into the agent's context.
  • Capability inventory: Read, Write, and Bash (file system manipulation).
  • Sanitization: No explicit validation or sanitization of the file content is performed before the agent processes it.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 5, 2026, 11:46 PM