The Agent Skills Directory

[SAFE]: The skill is a template for financial evaluation and diligence. Analysis revealed no malicious command execution, data exfiltration, or persistence mechanisms. The instructions are consistent with the skill's stated purpose.
[NO_CODE]: The skill consists exclusively of markdown instructions and metadata. It does not include any scripts, libraries, or executable binaries.
[PROMPT_INJECTION]: The skill is designed to process untrusted external data (such as company filings and earnings transcripts), which constitutes an attack surface for indirect prompt injection. This is addressed through internal controls.
Ingestion points: The skill ingests external revenue models, customer metrics, and public filing data as defined in SKILL.md.
Boundary markers: Both prompt.md and SKILL.md contain explicit instructions to "Separate facts from management claims, market narrative, and your own assumptions."
Capability inventory: The skill relies on standard agent capabilities; no specific tool calls or restricted operations are defined in the frontmatter.
Sanitization: The guides/qa-checklist.md and SKILL.md mandate that missing or stale data be disclosed and that "fake precision" be avoided, acting as a logical validation step for external data.

investment-analyst