The Agent Skills Directory

[METADATA_POISONING]: The skill's metadata contains several deceptive claims. The frontmatter specifies risk: safe and source_type: official, which are authoritative claims that contradict the presence of unverified external dependencies. Additionally, the listed author target1m in SKILL.md contradicts the identified skill author, suggesting potential impersonation or misleading provenance.
[EXTERNAL_DOWNLOADS]: The skill requires a connection to a remote Model Context Protocol (MCP) server at https://mcp.traderspy.app/mcp. This server provides the tool definitions and data for technical analysis, derivatives, and trader positions. As the traderspy.app domain is not a recognized trusted vendor or well-known service, it represents an unverified remote dependency that handles sensitive financial information provided by the user.
[INDIRECT_PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection via tool output poisoning.
Ingestion points: The agent processes data from the get_technical_indicators, get_derivatives, and get_positions tools, all of which fetch content from the external traderspy.app server.
Boundary markers: The skill provides a rigid reporting template to structure the agent's output, which partially mitigates accidental obedience but does not prevent malicious instructions within the tool data from influencing the agent's reasoning.
Capability inventory: The skill is configured for read-only market data analysis and does not currently include tools for trade execution or file system modification.
Sanitization: There is no evidence of sanitization or schema validation for the data returned by the external MCP server before it is incorporated into the agent's context.

traderspy-position-check