skills/yulonghe97/ystack/docs/Gen Agent Trust Hub

docs

Pass

Audited by Gen Agent Trust Hub on Apr 26, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands such as git diff, git symbolic-ref, and grep to analyze the repository state and verify documentation links. These commands are used for read-only inspection of the local environment.\n- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it reads and processes external project files to inform its documentation tasks.\n
  • Ingestion points: The agent reads from .context/<feature-id>/DECISIONS.md, .context/<feature-id>/PLAN.md, and .ystack/progress/<module>.md to understand feature requirements and implementation status.\n
  • Boundary markers: There are no instructions provided to separate the content of these files from the agent's system instructions or to treat them as untrusted data.\n
  • Capability inventory: The agent can modify project documentation files, structural configuration files (like CLAUDE.md), and execute local shell commands.\n
  • Sanitization: No sanitization or validation logic is defined for the content ingested from the project context files.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 26, 2026, 07:52 AM
Security Audit — agent-trust-hub — docs