The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill requires the installation of the forgejo-pp-cli tool. It provides instructions to use npx -y @mvanhorn/printing-press-library install forgejo or go install github.com/mvanhorn/printing-press-library/library/developer-tools/forgejo/cmd/forgejo-pp-cli@latest. These resources belong to the vendor 'mvanhorn'.
[REMOTE_CODE_EXECUTION]: Setup involves executing code from remote sources via npx and go install, which downloads and runs binaries from the author's repositories.
[DATA_EXFILTRATION]: The CLI includes a --deliver webhook:<url> flag. This feature allows the agent to automatically POST command results—which may contain sensitive code, issue details, or Forgejo configuration—to any user-specified URL. This presents a high risk for data exfiltration if an attacker can influence the destination URL.
[PROMPT_INJECTION]: The skill processes untrusted content from Forgejo instances (e.g., issue descriptions, pull requests, and notifications) that could contain malicious instructions (Indirect Prompt Injection).
Ingestion points: Data is pulled from Forgejo issues, pull requests, and notification threads in files such as SKILL.md (e.g., issue dashboard, notification inbox).
Boundary markers: The skill does not define specific delimiters or instructions to ignore embedded commands in the processed data.
Capability inventory: The CLI has the ability to write to the local file system, send data to external webhooks, and perform administrative actions on Forgejo instances (e.g., creating users or organizations).
Sanitization: There is no evidence of sanitization or validation of the external content before it is processed or used in subsequent agent actions.

pp-forgejo