crypto
Pass
Audited by Gen Agent Trust Hub on Sep 24, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted input from command-line arguments and file contents, which creates an attack surface for indirect prompt injection if the output (such as decrypted plaintext) is subsequently interpreted by the agent as instructions.
- Ingestion points: The
hash.js,encrypt.js, anddecrypt.jsscripts take arbitrary strings and file paths via CLI arguments. - Boundary markers: There are no explicit delimiters or instruction-ignore markers wrapping the output provided to the agent.
- Capability inventory: The skill allows reading files from the workspace (for hashing/decryption) and writing files (for encryption output and key generation).
- Sanitization: Input content is treated as raw data for cryptographic operations without specific filtering for malicious linguistic patterns.
Audit Metadata