v0.1.0

Finance Search Agent Strategy

BenignClawScan verdict for this skill. Analyzed May 1, 2026, 5:44 AM.

Analysis

This is a prompt-only finance research skill that is broadly coherent, with noteworthy reliance on external search tools and search-result authority.

GuidanceThis skill appears safe to install as an instruction-only research prompt. Before using it for important finance decisions, make sure outputs include citations, multiple-source verification, and clear uncertainty rather than relying uncritically on search results.

Findings (2)

Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.

Abnormal behavior control

Checks for instructions or behavior that redirect the agent, misuse tools, execute unexpected code, cascade across systems, exploit user trust, or continue outside the intended task.

Tool Misuse and Exploitation

SeverityLowConfidenceHighStatusNote

SKILL.md

prioritize calling `discover_tools` and `execute_search_tool` sequentially

The skill instructs the agent to use tool discovery and search execution tools. This is consistent with a search/research skill, but it means the agent may initiate external search workflows through whatever tools are available.

User impactThe agent may perform external searches or use available search tools while completing finance research tasks.

RecommendationInstall only if you are comfortable with the agent using available search tools, and review the agent's planned searches when the topic is sensitive.

Sensitive data protection

Checks for exposed credentials, poisoned memory or context, unclear communication boundaries, or sensitive data that could leave the user's control.

Memory and Context Poisoning

SeverityLowConfidenceHighStatusNote

SKILL.md

Real-time information returned by external tools is the only source of truth... you must unconditionally adopt the search results

The skill tells the agent to strongly trust retrieved external information. For a research skill this is understandable, but untrusted or low-quality search results could be over-weighted if not cross-checked.

User impactIf search results are inaccurate, manipulated, or incomplete, the final research report may repeat those errors.

RecommendationAsk the agent to cite sources, compare multiple reputable references, and flag uncertainty instead of treating a single search result as definitive.