The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses shell commands to deploy generated HTML content to Netlify. It also utilizes an inline Python script to parse a local JSON state file (.netlify/state.json) to retrieve the site ID for renaming operations. These commands are consistent with the skill's primary purpose of proposal deployment.
[EXTERNAL_DOWNLOADS]: The skill uses npx --yes to download and execute the netlify-cli package from the official npm registry. Netlify is a well-known cloud service, and this download is a standard part of its deployment workflow.
[INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from the user in the form of existing quotes and proposals for critique and reframing.
Ingestion points: Identified in SKILL.md (Step 0 and Step 1), where users are invited to paste external proposal content.
Boundary markers: The instructions do not define explicit delimiters or use specific system instructions to disregard commands embedded within the pasted data.
Capability inventory: The skill has access to shell execution and network operations via netlify-cli and python3 in SKILL.md (Step 6).
Sanitization: No explicit sanitization or input validation is performed on the ingested text before it is processed by the agent or included in the output HTML.

proposal-generator