The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: Fetches the squarespace-pp-cli tool from the vendor's GitHub repository or via npx from the @mvanhorn scope. These are resources provided by the skill author.
[COMMAND_EXECUTION]: Runs the squarespace-pp-cli binary to perform management tasks on Squarespace resources.
[DATA_EXPOSURE]: Accesses a sensitive session cookie file located at ~/.config/squarespace/account-cookie.txt to authenticate account dashboard commands.
[DATA_EXFILTRATION]: Provides a --deliver webhook:<url> option that allows command results to be transmitted to an external URL.
[INDIRECT_PROMPT_INJECTION]: The skill processes potentially untrusted data from Squarespace APIs, creating an attack surface for indirect prompt injection.
Ingestion points: API responses containing order details, customer profiles, and transaction summaries (SKILL.md).
Boundary markers: No specific delimiters or safety instructions are defined to separate untrusted data from agent instructions (SKILL.md).
Capability inventory: The skill can write to the local file system and perform network POST requests via the --deliver flag (SKILL.md).
Sanitization: There is no evidence of filtering or escaping external content before it is processed by the agent (SKILL.md).

pp-squarespace