The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses the Bash tool to execute git log and grep commands. This is consistent with its stated purpose of scanning the codebase and version history for secrets.
[DATA_EXFILTRATION]: While the skill accesses sensitive files (credentials, .env), it does not include any network-related tools or commands (e.g., curl, wget) to send this data externally. The output instructions explicitly request masking the secrets (showing only first/last characters).
[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted content from the local file system and Git history. While it lacks explicit boundary markers or sanitization logic for the data it reads, the risk is mitigated by the narrow scope of its search patterns and the structured nature of its output format.

secrets-guard