The Agent Skills Directory

[SAFE]: No malicious patterns, obfuscation, or data exfiltration techniques were detected in the skill instructions.
[NO_CODE]: The skill consists entirely of natural language instructions and does not include any scripts, binaries, or executable commands.
[PROMPT_INJECTION]: The skill processes untrusted user input for analysis, which constitutes a standard surface for indirect prompt injection.
Ingestion points: User-provided text passed through the /hitchcock command or selection.
Boundary markers: None present; the agent is instructed to review the text directly.
Capability inventory: None. The skill has no access to the file system, network, or shell environment.
Sanitization: None provided, though the lack of capabilities limits the potential impact of any injected instructions to the generated text output only.

hitchcock