officialese-penman

Warn

Audited by Gen Agent Trust Hub on Jul 31, 2026

Risk Level: MEDIUMCOMMAND_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The SKILL.md file contains instructions for the agent to invoke the shell to run the bundled scripts/check_placeholders.py script for document validation.
  • [DATA_EXFILTRATION]: The script scratch/parse_html.py contains hardcoded absolute paths pointing to a specific local user directory (/Users/zhangxin/). These paths reference internal data structures of the Antigravity IDE (.gemini/antigravity/brain/), which could lead to unauthorized access or exposure of local file metadata and session content.
  • [PROMPT_INJECTION]: The skill processes external, untrusted user materials to generate text, which represents an indirect prompt injection surface.
  • Ingestion points: User-provided source materials for generating prefaces and reports, processed as described in SKILL.md.
  • Boundary markers: Not present; there are no specific instructions or delimiters used to prevent the agent from following commands embedded within user-provided text.
  • Capability inventory: Shell command execution and file system read/write via bundled Python scripts.
  • Sanitization: None detected; the skill interpolates user input directly into generation prompts without validation.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Jul 31, 2026, 03:24 AM
Security Audit — agent-trust-hub — officialese-penman