aob-signatures

Warn

Audited by Gen Agent Trust Hub on Nov 13, 2026

Risk Level: MEDIUMEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs the user to install a third-party Python package from the official registry (PyPI) which is not authored by a recognized trusted vendor or the skill's author.
  • Evidence: pip install game-re-sigtool in SKILL.md.
  • [EXTERNAL_DOWNLOADS]: The documentation references several third-party GitHub repositories for external tools and scripts that have not been verified.
  • Evidence: Links to github.com/A200K/IDA-Pro-SigMaker, github.com/Nukem9/SwissArmyKnife, and github.com/nosoop/ghidra_scripts in references/tools.md.
  • [INDIRECT_PROMPT_INJECTION]: The skill provides a significant attack surface for indirect prompt injection as it is designed to ingest and analyze untrusted binary data from external files.
  • Ingestion points: The skill analyzes binary files (game.exe, dump.bin) and user-provided configuration files (signatures.toml) using the sigtool utility.
  • Boundary markers: No specific boundary markers or instructions to ignore embedded commands within the ingested data are provided to the agent.
  • Capability inventory: The agent has the capability to execute shell commands (pip, sigtool) and perform file system operations.
  • Sanitization: There is no evidence of sanitization or safety checks performed on the data extracted from the binary files before it is processed by the agent's logic.
  • [COMMAND_EXECUTION]: The skill's primary workflow involves the execution of the sigtool command-line utility for file system analysis and signature verification.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Nov 13, 2026, 02:25 PM