The Agent Skills Directory

[DATA_EXFILTRATION]: The skill documents a --deliver webhook:<url> flag that allows the agent to POST command results to any external URL, creating a potential vector for data exfiltration. Additionally, the feedback command can automatically send local logs to a remote endpoint if the EXCHANGERATE_API_FEEDBACK_AUTO_SEND environment variable is set.
[EXTERNAL_DOWNLOADS]: The instructions direct the agent to install the exchangerate-api-pp-cli tool using npx from the @mvanhorn scope or go install from the vendor's GitHub repository.
[COMMAND_EXECUTION]: The skill is designed to execute the exchangerate-api-pp-cli binary with various subcommands and flags based on user input.
[INDIRECT_PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection through external API data and natural language command discovery.
Ingestion points: External exchange rate data and natural language queries for the which command in SKILL.md.
Boundary markers: No explicit markers or delimiters are defined for processed data.
Capability inventory: Includes network operations (webhooks, API), local file writing (profiles, feedback logs), and shell command execution.
Sanitization: No sanitization or validation of external input is specified.

pp-exchangerate-api