Ae4
- Category
- analysis-evasion
- Confidence
- 80% confidence
- Finding
Suspicious Unicode normalization or mixed-script content
- Content
Security audit
Security checks for vulnerabilities and agentic risk
This skill is coherent as an investment-analysis workflow, but it can automatically change persistent investment files and gives ambiguous high-stakes trading guidance.
Install only if you want an agent to maintain and modify your local investment research files. Before use, require explicit confirmation before any edit or rewrite, keep backups or version control, and treat any profit forecasts, PE judgments, or buy/sell ranges as non-professional investment analysis rather than trading advice.
Suspicious Unicode normalization or mixed-script content
The skill is described as a workflow manager, but it expands into producing substantive weekly investment research with firm judgments, profit forecasts, and portfolio-maintenance outputs. Scope drift like this is risky because a user invoking a benign-sounding workflow skill may trigger high-stakes financial analysis and decision-support behavior beyond what they reasonably expected.
The trigger phrases are very broad and overlap with ordinary requests like 'analyze new material' or 'update stock pool.' Broad activation criteria increase the chance that this skill auto-runs in situations where the user did not intend financial-workflow execution, file mutation, or cross-skill invocation, causing overreach and unintended actions.
The skill directs the agent to append, update, and write multiple repository files as a mandatory step, but it does not require explicit user confirmation or warn that persistent changes will be made. In an agent environment, this creates a real integrity risk: ordinary analysis requests can silently mutate tracked files, archives, and evaluation artifacts.
The instruction to rewrite the consolidated evaluation file without preserving the old version or warning about overwrite behavior is destructive by design. If followed automatically, it can erase historical assessments, reduce auditability, and permanently replace prior judgments with newer output that may be incomplete or wrong.
This section gives conflicting instructions: it says not to provide buy/sell price guidance, then explicitly permits buy/sell ranges. Contradictory policy in an autonomous skill is dangerous because downstream agents may choose the more permissive branch and generate regulated or high-risk financial advice that the surrounding workflow appears to forbid.