The Agent Skills Directory

[DATA_EXFILTRATION]: The skill accesses sensitive credentials and performs network operations.
Accesses Binance.US API keys and secrets from local configuration files (~/.openclaw/secrets.env, .env).
Performs network requests to api.binance.us and news.google.com to fulfill its stated purpose.
These operations are consistent with the skill's primary function of providing account-aware market reports and do not involve untrusted third-party domains.
[PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection through external data ingestion.
Ingestion points: The scripts/binance_us_brief.py script fetches news headlines from the Google News RSS feed (news.google.com/rss/search) in the fetch_asset_news function.
Boundary markers: External content (headlines) is interpolated into the final output delivered to the agent without clear delimiters or instructions to ignore embedded commands.
Capability inventory: The skill script is executed by the agent and retrieves sensitive account information such as balances and trade history.
Sanitization: No sanitization or filtering of the headline text is performed before it is included in the output.

binance-us-briefing-engine