talisman

Pass

Audited by Gen Agent Trust Hub on Jul 17, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes local Python scripts (oklch_to_hex.py, prepare_logo.py) and system binaries (pdflatex, make, pdftoppm, pdftotext) to process project assets and compile the final PDF document as part of its core functionality.
  • [PROMPT_INJECTION]: The skill is subject to indirect prompt injection risks due to its requirement to read and process the codebase being documented.
  • Ingestion points: The agent performs extensive research on the codebase (Phase 2 in SKILL.md), including data models, features, and CSS/theme files.
  • Boundary markers: No specific boundary markers or instructions to ignore embedded commands within the analyzed code are defined.
  • Capability inventory: The skill possesses the capability to execute shell commands and Python scripts via the agent's runtime environment, specifically during Phase 7 (Build and verify) and Phase 3 (Scaffold).
  • Sanitization: No explicit sanitization or filtering of the content extracted from the codebase is mentioned before it is interpolated into LaTeX templates or passed to scripts.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 17, 2026, 02:22 PM
Security Audit — agent-trust-hub — talisman