The Agent Skills Directory

[PROMPT_INJECTION]: The skill processes untrusted external code files for analysis, creating a vulnerability surface for indirect prompt injection.
Ingestion points: The scripts/check_intervals.py script reads and analyzes content from user-specified file paths. Additionally, the manual workflow in SKILL.md instructs the agent to review code provided by the user.
Boundary markers: The instructions lack explicit requirements for the agent to use protective delimiters (such as XML tags) or to ignore instructions found within the analyzed code comments or strings.
Capability inventory: The skill has the capability to read local files and execute a local Python script for static analysis.
Sanitization: There is no evidence of content sanitization or instruction filtering applied to the ingested files before they are presented to the agent's reasoning engine.
[COMMAND_EXECUTION]: The skill requires the execution of a local Python script for its primary functionality.
Evidence: SKILL.md contains instructions to execute python scripts/check_intervals.py to perform automated security checks on a directory or file.
Context: The script is a local vendor-provided resource (ArabelaTso) that performs static regex-based analysis using regular expressions and does not interact with the network or execute the target code.

critical-interval-security-checker