The Agent Skills Directory

[SAFE]: No malicious patterns or high-risk operations were detected. The skill is focused on text manipulation for document generation.
[NO_CODE]: This skill consists entirely of configuration files and markdown instructions. It does not include any executable scripts or binary files, significantly reducing the attack surface.
[PROMPT_INJECTION]: While the skill ingests untrusted transcript data, it is evaluated as safe for indirect prompt injection risks. Ingestion points: Raw chat transcripts and interview notes (SKILL.md). Boundary markers: Absent; there are no instructions to the agent to treat input as untrusted or ignore embedded commands. Capability inventory: No high-risk capabilities detected; the skill does not use subprocesses, file writes, or network calls. Sanitization: Absent; the skill performs structural transformation but no explicit sanitization for injection patterns.

write-transcript