The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill defines a workflow where the AI agent is instructed to fetch and analyze information from external manufacturer websites and GitHub repositories. This behavior creates a potential surface for indirect prompt injection if those external resources were to be compromised or contain malicious payloads designed to influence the agent.
Ingestion points: SKILL.md (Step 2) directs the agent to load manufacturer references and project documentation from remote URLs.
Boundary markers: The skill provides structured templates (templates/camera-assessment.md) which serve as delimiters for organizing assessment findings.
Capability inventory: The skill itself contains no executable code; it leverages the agent's built-in web browsing and analysis tools.
Sanitization: The instructions do not explicitly include steps for sanitizing content retrieved from the web before processing it.
[NO_CODE]: The entire skill package consists of Markdown documentation, JSON data files, and templates. It does not include any executable scripts (e.g., Python, Bash, JavaScript), significantly reducing the risk of local command execution or malware persistence.

camera-hacking