The Agent Skills Directory

[SAFE]: The skill uses the 'longbridge' command-line interface, which is a resource provided by the skill's author ('longbridge'). The commands used (longbridge news, longbridge financial-report, and longbridge industry-valuation) are focused on read-only financial data retrieval.
[SAFE]: No indicators of prompt injection, data exfiltration, or malicious command execution were detected. The skill's operations are consistent with its stated purpose of industry analysis.
[SAFE]: While the skill ingests external data (news and financial reports) which could technically serve as a surface for indirect prompt injection, this behavior is essential to its primary function. The skill does not possess high-privilege capabilities (like file system writes or arbitrary network requests) that could be exploited via such an injection.
Ingestion points: Industry news and financial data retrieved via the longbridge CLI as described in the workflow (SKILL.md).
Boundary markers: None present.
Capability inventory: Limited to the provided longbridge CLI read commands (SKILL.md).
Sanitization: No explicit sanitization of news content is mentioned.

longbridge-supply-chain