dcf-valuation
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted user input regarding financial metrics and stock names, creating a vulnerability surface for indirect prompt injection.
- Ingestion points: The skill processes user prompts containing stock tickers, PE/PB ratios, and DCF parameters (defined in
SKILL.mdand demonstrated intest-prompts.json). - Boundary markers: The instructions do not implement explicit delimiters or "ignore embedded instructions" warnings to separate user data from the agent's core reasoning logic.
- Capability inventory: No risky capabilities were detected; the skill does not use
allowed-tools, perform file writes, initiate network operations, or execute subprocesses. - Sanitization: There is no evidence of input validation, sanitization, or escaping for user-supplied content before it is interpolated into the agent's context.
Audit Metadata