The Agent Skills Directory

[Prompt Injection] (SAFE): No instructions found that attempt to bypass safety filters, extract system prompts, or override agent behaviors. The guidelines emphasize clarity and objective-driven behavior.
[Data Exposure & Exfiltration] (SAFE): No hardcoded credentials, sensitive file path access, or network operations were detected. The example files contain generic placeholders and broken local links for demonstration purposes only.
[Indirect Prompt Injection] (INFO): The skill is designed to process untrusted data (external agent prompt files).
Ingestion points: The agent is instructed to read files like agents.md as described in SKILL.md.
Boundary markers: Absent; the skill does not specify delimiters for the data being reviewed.
Capability inventory: None; the skill contains no scripts or tools to execute commands, write files, or access the network.
Sanitization: Absent; however, since there are no functional side effects or executable capabilities, the ingestion of untrusted prompt text for review purposes poses negligible risk.
[No Code] (SAFE): The skill consists entirely of Markdown files (.md). There are no Python scripts, Node.js packages, or shell scripts included in the package.

agent-prompt-validator