Security audit
Security checks for vulnerabilities and agentic risk
This is a text-only startup review skill whose file and search use is disclosed and aligned with its purpose.
Before using it, remove credentials, bank details, customer lists, unpublished contracts, and other unnecessary confidential material from startup documents. Use it for diagnostic review, not as legal, tax, valuation, securities, transaction, or investment advice.
Skill instructs the agent to omit warnings, disclaimers, or ethical commentary. Stripping safety caveats hides risk from the user and is a common jailbreak preamble.
## Fundraising Story
Judge whether the current facts form a coherent reason for capital now and a
credible next milestone. Do not judge financing probability.
Inspect whether these parts connect:
Skill instructs the agent to omit warnings, disclaimers, or ethical commentary. Stripping safety caveats hides risk from the user and is a common jailbreak preamble.
## Fundraising Story
Judge whether the current facts form a coherent reason for capital now and a
credible next milestone. Do not judge financing probability.
Inspect whether these parts connect:
This markdown file defines natural-language triggers, so SQP-1 applies. Phrases like "What is weak in this project?" and "Review this pitch deck" are broad and could match many general critique or document-review situations without clearly delimiting when this specific startup-investor-focused skill should activate.
Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.
smallest useful substitute.
Ask four to eight concise questions. Every question must concern the project or
idea, not the assistant's preferred workflow. Do not ask the user to choose an
analysis angle or select between business, deck, narrative, or meeting review.
Useful question areas include:
The skill enables implicit invocation without any visible trigger constraints, allowing the agent to auto-select this skill based on broad semantic matches rather than explicit user intent. Because this skill analyzes startup materials that may include sensitive business plans, fundraising strategy, and pitch content, unintended invocation could cause unnecessary exposure of private data to the skill or produce unsolicited analysis in contexts where the user did not mean to use it.
Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.
smallest useful substitute.
Ask four to eight concise questions. Every question must concern the project or
idea, not the assistant's preferred workflow. Do not ask the user to choose an
analysis angle or select between business, deck, narrative, or meeting review.
Useful question areas include:
No suspicious patterns detected.