The Agent Skills Directory

[PROMPT_INJECTION]: No attempts to override system instructions or bypass safety guardrails were detected in the skill's logic or documentation.
[DATA_EXPOSURE_EXFILTRATION]: No sensitive file paths, hardcoded credentials, or unauthorized network operations were found. The skill references other tools within the same vendor ecosystem (e.g., apply-profile-reader, apply-sop-writer) for data integration, which is standard for specialized agent skills.
[OBFUSCATION]: The content is clear and readable. No hidden characters, Base64 encoding, homoglyphs, or steganographic techniques were detected.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process user-provided application materials and interview responses.
Ingestion points: Data enters through companion skills (apply-profile-reader, apply-program-fit-mapper) and direct user interaction during mock rehearsals (Steps 1, 4, and 7).
Boundary markers: The instructions do not define specific delimiters for untrusted user content.
Capability inventory: No file system write, network exfiltration, or arbitrary command execution capabilities were identified in the provided files.
Sanitization: No explicit sanitization or filtering of user-provided content is performed before processing.
[EXTERNAL_DOWNLOADS]: The skill contains links to reputable academic and professional sources (e.g., Stanford University, UT Austin, and DDI) to provide evidence for its methodologies. These references are used solely for instructional purposes and do not involve remote code execution.

apply-interview-prep