crypto-rsa-attacks

Pass

Audited by Gen Agent Trust Hub on Sep 20, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill provides specific instructions for executing local command-line tools for cryptographic analysis.\n
  • The methodology uses openssl to extract parameters from PEM files.\n
  • The skill recommends rsactftool for automated triage and exploitation of various RSA vulnerabilities.\n- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted cryptographic parameters which represents a potential attack surface.\n
  • Ingestion points: The skill extracts parameters (n, e, c) from potentially untrusted sources like PEM files, JWT tokens, or external text inputs as described in the extraction steps in SKILL.md.\n
  • Boundary markers: There are no specified delimiters to isolate external data from the agent's instructions.\n
  • Capability inventory: The skill uses openssl, rsactftool, and Python scripts involving pycryptodome and sympy.\n
  • Sanitization: The instructions do not include steps for sanitizing or validating the format of extracted values before tool execution.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 20, 2026, 11:01 PM
Security Audit — agent-trust-hub — crypto-rsa-attacks