The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from signal records and the Financial Modeling Prep (FMP) API, which is then incorporated into reports consumed by the AI agent.
Ingestion points: Local signal files (.json) and historical price data fetched from the financialmodelingprep.com API.
Boundary markers: The skill does not employ specific delimiters or "ignore instructions" warnings when interpolating external data into its Markdown and YAML reports.
Capability inventory: The skill is capable of performing network requests and writing files to the local reports/ directory.
Sanitization: No evidence was found of sanitization or escaping for fields like ticker, outcome_notes, or API responses before they are included in generated reports.
[EXTERNAL_DOWNLOADS]: The skill fetches historical stock price data from financialmodelingprep.com. This is a well-known financial data service, and the operation is central to the skill's stated purpose of signal postmortem analysis.

signal-postmortem