The Agent Skills Directory

[SAFE]: The skill performs basic, non-privileged operations consistent with its stated purpose of processing input and outputting a length value. There is no evidence of obfuscation, remote code execution, or persistence mechanisms.
[INDIRECT_PROMPT_INJECTION]: The skill possesses a data ingestion surface in scripts/process.py which could process untrusted file content. However, the risk is negligible as the script merely calculates the character length of the input. * Ingestion points: scripts/process.py reads the content of a file specified by a command-line argument. * Boundary markers: No delimiters are used, but the content is not interpolated into a prompt. * Capability inventory: The script has read access to the local file system to process the target file. * Sanitization: The ingested data is used only for length calculation and is not executed or presented to the agent in a way that allows for instruction override.

good-skill