The Agent Skills Directory

[EXTERNAL_DOWNLOADS] (MEDIUM): The skill suggests using npx -y @grimoirelabs/cli and mentions @grimoirelabs/venues. These packages are downloaded from the npm registry at runtime. Since the '@grimoirelabs' organization is not in the list of trusted sources, this introduces a supply-chain risk where malicious code could be introduced via the external package.
[COMMAND_EXECUTION] (LOW): The skill performs shell command execution using the grimoire CLI and npx. This is functional but provides a surface for command injection if user inputs (like RPC URLs) are not properly sanitized by the underlying agent.
[INDIRECT_PROMPT_INJECTION] (LOW):
Ingestion points: The skill fetches metadata from the external API endpoint https://api-v2.pendle.finance/core.
Boundary markers: Absent; there are no instructions to delimit or ignore instructions embedded within the fetched metadata.
Capability inventory: The skill has the ability to execute shell commands and fetch data from the network.
Sanitization: Absent; the skill does not explicitly describe any sanitization or validation of the remote API response before it is used by the agent.

grimoire-pendle