The Agent Skills Directory

[DATA_EXFILTRATION] (HIGH): Access to sensitive credential files.
Evidence: The skill executes grep -q "STRIPE_" .env.local and similar commands for Bitcoin and Lightning providers. Accessing .env.local files is a high-severity risk as these files are standard locations for plaintext API keys and secrets.
[COMMAND_EXECUTION] (LOW): Execution of shell commands for system reconnaissance.
Evidence: The Provider Detection block uses grep, env, and command -v to probe the environment. These commands are used to inspect the file system and environment state.
[INDIRECT_PROMPT_INJECTION] (HIGH): Vulnerability surface through untrusted data ingestion.
Ingestion points: Local files package.json and .env.local are read by the skill's discovery scripts.
Boundary markers: None. There are no delimiters or instructions to ignore embedded content within the files being scanned.
Capability inventory: The skill has the capability to execute shell commands (grep, env) and access the file system.
Sanitization: None. The skill does not sanitize the contents of the files before processing them with shell utilities, which could lead to command injection if file contents are maliciously crafted.

check-payments