The Agent Skills Directory

[Indirect Prompt Injection] (HIGH): The skill is highly vulnerable to instructions embedded in the data it is designed to analyze (error logs and issue reports).
Ingestion points: The issue argument and the use of 'Read' for error log analysis as described in SKILL.md.
Boundary markers: No delimiters or isolation instructions are present to differentiate between the user's problem description and the agent's internal instructions.
Capability inventory: The skill explicitly leverages Bash for runtime diagnostics and has the capability to 'Apply fixes' (file/system modification) as stated in SKILL.md.
Sanitization: There is no evidence of sanitization, escaping, or validation of the external content before it is processed by the agent's logic or passed to shell tools.
[Command Execution] (MEDIUM): The integration of 'Bash for runtime diagnostics' introduces a risk of arbitrary command execution if the agent is manipulated by malicious input found within the logs or issue descriptions it processes.

sc-troubleshoot