The Agent Skills Directory

[SAFE] (SAFE): No malicious patterns such as prompt injection, obfuscation, or hardcoded credentials were detected in the skill definition.
[DATA_EXFILTRATION] (SAFE): The automated scanner alert for 'logger.info' is a false positive; the string is used as a replacement pattern in a code example, not as a network destination.
[COMMAND_EXECUTION] (LOW): The skill executes a local Python script scripts/ast_grep_find.py via Bash. This is standard functionality for this tool, though it requires the wrapper script to safely handle user-supplied search and replacement patterns to prevent command injection.
[INDIRECT_PROMPT_INJECTION] (LOW): The skill is designed to process untrusted codebases, which presents an attack surface. 1. Ingestion points: Local source code files specified by the --path and --glob parameters. 2. Boundary markers: No explicit separators or instructions to ignore embedded commands are defined. 3. Capability inventory: The skill has the ability to execute Bash commands and Read local files. 4. Sanitization: Relies on the external ast-grep utility and the local wrapper script's implementation.

ast-grep-find