The Agent Skills Directory

[DATA_EXFILTRATION]: The skill's primary functionality involves sending sensitive cryptographic parameters—such as private keys for digital signatures, secrets for HMAC computation, and keys for AES encryption—to the vendor's remote API endpoint at api.agentpmt.com for processing.
[EXTERNAL_DOWNLOADS]: The documentation recommends the installation of supplemental components from the vendor's GitHub repository (AgentPMT/agent-skills) using the npx skills command.
[PROMPT_INJECTION]: The skill possesses an attack surface for indirect prompt injection because it processes external data provided by the user or other tools.
Ingestion points: The value parameter in the hash, hmac, sign, encrypt, and decrypt actions (defined in SKILL.md and schema.md) serves as the entry point for untrusted data.
Boundary markers: The prompt instructions and schemas lack explicit boundary markers or directions for the agent to ignore any instructions embedded within the processed data.
Capability inventory: The skill is capable of network operations via its integration with the AgentPMT-hosted remote execution infrastructure.
Sanitization: There is no documentation regarding the sanitization or validation of the input data before it is utilized in cryptographic operations or transmitted to the remote API.

encrytion-decryption-toolkit