The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill fetches business and ad account information from Spotify's partner API to assist the user in selection. This ingestion of external data creates a surface for indirect prompt injection if the API response were to contain malicious instructions.
Ingestion points: Data retrieved from GET /businesses and GET /businesses/{business_id}/ad_accounts in SKILL.md.
Boundary markers: Absent; there are no specific delimiters or instructions to ignore embedded commands within the API data.
Capability inventory: The skill possesses significant capabilities, including shell execution (bash), Python script execution, and file system modifications (Write, Edit).
Sanitization: The instructions do not specify any validation or escaping for the data retrieved from the API before it is processed by the agent.
[COMMAND_EXECUTION]: The skill uses the Bash tool to execute security add-generic-password for keychain management and curl for verifying the configuration against Spotify's servers.
[CREDENTIALS_UNSAFE]: While the skill correctly avoids storing the client_secret in plaintext files, it passes the secret as a command-line argument to the security command and the local Python helper scripts. This can potentially leak the secret to other users on the system via process listing tools or shell history logs.

configure