The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill downloads and installs software components from the author's infrastructure, specifically using go install for GitHub repositories under github.com/mvanhorn/ and npx for packages in the @mvanhorn npm scope.
[COMMAND_EXECUTION]: The skill instructions direct the agent to install and run the github-intel-pp-cli and github-intel-pp-mcp binaries to perform data retrieval and search operations.
[DATA_EXFILTRATION]: The CLI tool includes a --deliver webhook:<url> feature that enables the agent to POST command results to arbitrary external HTTP endpoints, which could be used to transmit data outside the local environment.
[PROMPT_INJECTION]: The skill is subject to indirect prompt injection risks as it ingests untrusted data from public GitHub repositories and security advisories.
Ingestion points: GitHub security advisories and repository metadata retrieved via the advisories and repos commands.
Boundary markers: No explicit delimiters or instructions to ignore embedded commands are present in the processing logic.
Capability inventory: The agent has the ability to write output to local files (file:<path>) and send data to external URLs (webhook:<url>).
Sanitization: The skill does not define specific sanitization or validation steps for the retrieved GitHub content before it is processed by the agent.

pp-github-intel