The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes local shell commands to run repository-specific Python tools (e.g., tools/financial_rigor.py, tools/twstock_data.py, tools/report_audit.py) for financial metric validation, stock data retrieval, and report auditing. It also utilizes the system date command for temporal baselining of financial data.
[INDIRECT_PROMPT_INJECTION]: The skill possesses an attack surface for indirect prompt injection due to its core function of ingesting and analyzing untrusted external content.
Ingestion points: The skill is instructed to fetch raw earnings reports, conference call transcripts, and investor day materials from external websites such as Seeking Alpha, SEC EDGAR, IR pages, and community forums like Xueqiu (雪球).
Boundary markers: There are no explicit instructions or delimiters defined to separate the untrusted external content from the agent's internal instructions, nor are there warnings to ignore embedded instructions within the fetched data.
Capability inventory: The skill has access to shell execution (via repository tools) and the ability to write analysis reports to the local reports/ directory.
Sanitization: The instructions do not specify any sanitization, filtering, or escaping of the external text before it is processed by the AI agent.

earnings-review