The Agent Skills Directory

[SAFE]: The skill consists entirely of markdown-based documentation and architectural guidance. It does not include any scripts, executable commands, or external dependencies.
[SAFE]: No evidence of prompt injection, data exfiltration, or obfuscation was found. The instructions are focused on guiding the agent to assess account recovery procedures.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to process user-provided descriptions of authentication flows for review. While this constitutes an attack surface where a user could provide malicious input to influence agent behavior, the skill lacks tool-based capabilities (such as file writing or network requests) that would make such an injection exploitable. In its current form, the risk is negligible.
Ingestion points: User-provided recovery flow descriptions (SKILL.md)
Boundary markers: None present
Capability inventory: No tools or subprocess calls identified
Sanitization: Not applicable as no processing or interpolation occurs

account-recovery