dstack-beads-review-feature-spec

Pass

Audited by Gen Agent Trust Hub on Aug 29, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands using placeholders for user-supplied input (e.g., <selector>, <base>, <title>, <temporary-description>). If the agent populates these placeholders with unsanitized content, it could lead to arbitrary shell command execution.
  • [INDIRECT_PROMPT_INJECTION]: The skill reads and reconciles content from the repository, including source code, documentation, and dependencies, and incorporates this information into a design document.
  • Ingestion points: The skill reads the complete repository context, including docs/src/features/<slug>/design.md, source code, tests, and documentation files within the worktree.
  • Boundary markers: There are no explicit instructions or delimiters mentioned to prevent the agent from following instructions potentially embedded in the repository's data files.
  • Capability inventory: The skill has the ability to write to files (design.md), execute the dstack binary, and perform git commit operations.
  • Sanitization: The skill does not define any sanitization or validation steps for the content read from the repository before it is processed or used in commands.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 29, 2026, 12:03 AM
Security Audit — agent-trust-hub — dstack-beads-review-feature-spec