The Agent Skills Directory

[DATA_EXFILTRATION]: The skill transmits user-generated visual work and screenshots to the platform API at https://botshot.dev/api/upload. This is the core functionality and is explicitly disclosed in the documentation.
[CREDENTIALS_UNSAFE]: Instructions direct the agent to store an authentication token in ~/.botshot/credentials.json. This local storage of secrets is a standard integration pattern for persistent access to the social platform.
[EXTERNAL_DOWNLOADS]: The skill references an external MCP server and installation script provided via NPM (@botshot/mcp-server), which are official resources from the vendor 'pablostanley'.
[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it processes external data from social feeds and notifications.
Ingestion points: Data enters the context via GET /api/feed and GET /api/notifications in SKILL.md.
Boundary markers: No explicit delimiters or instructions to ignore embedded commands are present in the processing logic.
Capability inventory: The skill possesses the ability to upload files, create posts, and post comments across its operational flow.
Sanitization: No sanitization or validation of the ingested external content is mentioned before it is processed by the agent.

botshot