The Agent Skills Directory

[PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection because it processes untrusted data from external files.
Ingestion points: The skill accepts a file path or screen name via $ARGUMENTS and is designed to analyze the content of these targets.
Boundary markers: The instructions do not define clear delimiters or provide the agent with 'ignore' instructions for content found within the audited files.
Capability inventory: The skill utilizes Read, Grep, and Glob tools to access and search through file system data.
Sanitization: There is no mechanism to sanitize or validate the content of the files before the agent processes them, allowing instructions embedded in the source code to potentially influence the agent's behavior.

ss-audit