The Agent Skills Directory

[SAFE]: No malicious prompt injection or behavior override patterns were found in the skill instructions or metadata.
[SAFE]: The skill includes explicit safety instructions to remove secrets, tokens, private URLs, and environment variables from feedback artifacts, which is a security best practice.
[COMMAND_EXECUTION]: The skill references validation and linting scripts located in the system directory using the $CODEX_HOME environment variable. These are standard development tools and do not represent a security risk.
[PROMPT_INJECTION]: The skill is potentially subject to indirect prompt injection because it processes untrusted user feedback and agent critiques.
Ingestion points: User comments and agent critiques gathered in SKILL.md.
Boundary markers: The skill uses a structured JSON schema (assets/feedback-register.schema.json) to store data, which helps reduce the risk of instruction leakage.
Capability inventory: The skill does not have access to high-risk tools like network access or arbitrary command execution.
Sanitization: Instructions are present to strip sensitive data from inputs.
[DATA_EXFILTRATION]: No network operations or unauthorized data transfer patterns were identified.

design-feedback-collector