The Agent Skills Directory

[SAFE]: No malicious patterns, obfuscation, or safety bypass attempts were detected. The skill operates strictly within its described purpose of financial portfolio analysis.
[PROMPT_INJECTION]: The skill has an indirect prompt injection surface because it processes user-provided holdings data from portfolio.json or direct text input.
Ingestion points: The portfolio.json file and the task field in the user interface.
Boundary markers: The prompt template utilizes headers to separate user-provided materials from the agent's instructions.
Capability inventory: The skill is designed to invoke scripts/call_api.py from the associated pandadata-api skill for data retrieval.
Sanitization: Input content from the holdings list is analyzed for financial data without explicit string sanitization or filtering for embedded instructions.
[EXTERNAL_DOWNLOADS]: The skill defines a dependency on the pandadata-api skill, which is part of the same author's project ecosystem.
Evidence: The documentation references the quantskills/skill-pandadata-api repository and requires it for core functionality.
[DATA_EXFILTRATION]: The skill accesses a local data file, portfolio.json, to read stock symbols and weights. This access is a functional requirement for the skill's primary task and does not involve unauthorized access to sensitive system files or exfiltration to untrusted domains.

portfolio-checkup