Ae1
High
- Category
- analysis-evasion
- Confidence
- 100% confidence
- Finding
Referenced artifact was not completely inspected
- Content
md | 股票 | `ref/codes_stock.json` | 4579 |
Security audit
iFinD Excel Plugin
Security checks for vulnerabilities and agentic risk
Overview
This skill is a Chinese-language reference for generating iFinD Excel formulas, with no hidden execution, persistence, or credential handling found.
Install only if you use iFinD/同花顺 Excel workflows and are comfortable with Chinese reference data. Review generated formulas before opening or sharing workbooks, because Excel formulas may query financial data through your logged-in iFinD environment and a few catalog entries appear malformed.
Vulnerability Patterns
- Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
- Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
- Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
- Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
- Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
Vulnerability Patterns
- Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
- MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
- Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
- Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
- Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (26)
Ae1
High
- Category
- analysis-evasion
- Confidence
- 100% confidence
- Finding
Referenced artifact was not completely inspected
- Content
md | 港股 | `ref/codes_hk.json` | 1388 |
Ae1
High
- Category
- analysis-evasion
- Confidence
- 100% confidence
- Finding
Referenced artifact was not completely inspected
- Content
md | 债券 | `ref/codes_bond.json` | 3758 |
Ae1
High
- Category
- analysis-evasion
- Confidence
- 100% confidence
- Finding
Referenced artifact was not completely inspected
- Content
md | **全部指标** | `ref/codes_all.json` | **12859** |
Vague Triggers
Medium
- Category
- Not specified by scanner
- Confidence
- 95% confidence
- Finding
This entry appears to have corrupted or misaligned field text, with what looks like a transaction-date enumeration embedded into the human-readable name/description rather than a scoped parameter definition. In a skill used as a reference source for generating Excel formulas or data requests, ambiguous metadata can cause an agent to select the wrong field, misconstruct queries, or apply unintended broad date scopes, leading to incorrect or overbroad data retrieval.
- Content
Vague Triggers
Medium
- Category
- Not specified by scanner
- Confidence
- 95% confidence
- Finding
This finding shows the same corruption pattern: descriptive text for date options appears spliced into a field intended to describe the contract attribute, making the manifest ambiguous about what the function returns versus what arguments it accepts. Because this skill is meant to guide automated Excel data generation, such ambiguity can propagate into incorrect formula construction, unintended parameterization, or silent misuse of financial data fields.
- Content
Vague Triggers
Medium
- Category
- Not specified by scanner
- Confidence
- 90% confidence
- Finding
This JSON manifest entry contains what looks like a truncated trading-date option list split across the "name" and "description" fields rather than a clear, bounded indicator description. In a manifest file, such malformed natural-language metadata can make it unclear how the skill or option should be invoked and what inputs are valid, which matches the vague-trigger/unclear-scope category.
- Content
Vague Triggers
Medium
- Category
- Not specified by scanner
- Confidence
- 90% confidence
- Finding
The "ths_listed_date_option" entry repeats the same malformed pattern, with a partial enumeration of dates embedded into the display name and a cut-off description. Because this is a manifest-style JSON file, unclear metadata about accepted inputs or trigger scope can cause unintended or incorrect selection of this option.
- Content
Vague Triggers
Medium
- Category
- Not specified by scanner
- Confidence
- 89% confidence
- Finding
This entry again embeds a partial trading-date enumeration into the "name" while the "description" is truncated, so the valid input scope is not clearly documented. For a manifest file, missing specificity about allowable values and context is a genuine ambiguity risk under the vague-trigger rule.
- Content
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 97% confidence
- Finding
This JSON file is full of user-facing natural-language fields such as
name,description, andparamswritten exclusively in Chinese, beginning at L00004-L00006 and continuing throughout the file. Because the file provides no indication of user opt-in, alternate locale support, or a documented region-specific constraint, it risks violating a language/locale policy that forbids forcing a specific language by default.- Content
Vague Triggers
Medium
- Category
- Not specified by scanner
- Confidence
- 91% confidence
- Finding
This JSON manifest-like file uses the same generic description value "基本资料" across entries without any specific activation constraints, trigger phrases, or exclusion conditions. In a manifest file, such broad metadata can leave it unclear when a given item should be invoked versus not invoked, which matches the vague-trigger category.
- Content
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 91% confidence
- Finding
This JSON manifest-like file uses Chinese for names, descriptions, and parameter documentation throughout, with no indication that users can choose another language or that the locale restriction is intentional and justified. Under the policy rule for natural-language violations, forcing a specific language without user opt-in is a reportable issue.
- Content
Natural-Language Policy Violations
Low
- Category
- Not specified by scanner
- Confidence
- 83% confidence
- Finding
This JSON manifest-like file uses Chinese names and descriptions throughout, with no indication that the skill is region-specific or that users can opt into this locale. Under the natural-language policy check, a file that forces a specific language without user choice or documented justification can violate language/locale policy.
- Content
Natural-Language Policy Violations
Low
- Category
- Not specified by scanner
- Confidence
- 90% confidence
- Finding
This JSON file contains extensive natural-language labels and descriptions entirely in Chinese, starting with the user-facing field name at L00004. For a broadly reusable skill data file, that constitutes a locale-specific presentation choice without any visible opt-in, alternative locale, or justification that the dataset is intentionally China-specific.
- Content
Natural-Language Policy Violations
Low
- Category
- Not specified by scanner
- Confidence
- 89% confidence
- Finding
This JSON manifest-like file uses Chinese for names and descriptions throughout, but does not document that the skill is region-specific or offer any language/locale choice. Under the policy rule, forcing a specific language without user opt-in can be a natural-language policy concern.
- Content
Natural-Language Policy Violations
Low
- Category
- Not specified by scanner
- Confidence
- 89% confidence
- Finding
SQP-3 applies to all file types and covers language/locale policy violations. The file consistently uses Chinese names and descriptions for all entries, but does not document that the skill is intended only for Chinese-speaking users or offer any language/locale opt-in, which can force a specific language experience on users.
- Content
Natural-Language Policy Violations
Low
- Category
- Not specified by scanner
- Confidence
- 78% confidence
- Finding
This JSON manifest-like file contains user-facing names and descriptions almost entirely in Chinese, with no indication that the locale is optional, user-selectable, or specifically limited to a Chinese-language context. Under the policy rule for language/locale constraints, this can be a natural-language policy concern when a skill exposes only one language without opt-in or justification.
- Content
Natural-Language Policy Violations
Low
- Category
- Not specified by scanner
- Confidence
- 83% confidence
- Finding
This JSON manifest-like data uses Chinese natural-language names and descriptions throughout, with no indication that the skill is region-specific or that users can opt into this locale. Under the policy rule for natural-language violations, hard-coding a single language without documented choice or justification can be a locale-policy issue.
- Content
Natural-Language Policy Violations
Low
- Category
- Not specified by scanner
- Confidence
- 88% confidence
- Finding
All user-facing names and descriptions in this file are provided only in Chinese, with no indication of optional language selection or justification for a locale-specific constraint. For a general skill artifact, this can constitute a language/locale policy issue because it implicitly forces one language without user opt-in.
- Content
Vague Triggers
Low
- Category
- Not specified by scanner
- Confidence
- 84% confidence
- Finding
This JSON file is in scope for SQP-1 because it is a manifest-like .json file. The entry on these lines appears malformed, with the 'name' and 'description' fields containing fragmented invocation/parameter text rather than a clear, bounded description, making the activation or usage scope unclear.
- Content
Natural-Language Policy Violations
Low
- Category
- Not specified by scanner
- Confidence
- 93% confidence
- Finding
Natural-language fields such as "name" and "description" are consistently presented only in Chinese across the file, with no indication that the user can choose another language or that the locale restriction is intentional. This can violate language or locale policy when a skill implicitly forces one language without documented opt-in or justification.
- Content
Vague Triggers
Low
- Category
- Not specified by scanner
- Confidence
- 88% confidence
- Finding
This JSON manifest-like file repeatedly uses very short descriptions such as "/年行情", "/区间行情", and "/日行情" to describe entries, but it does not specify how these descriptions are intended to trigger or be selected. In a manifest file, such generic phrases are broad and lack negative examples or contextual constraints, which could cause accidental matching with common financial requests.
- Content
Natural-Language Policy Violations
Low
- Category
- Not specified by scanner
- Confidence
- 77% confidence
- Finding
This JSON manifest uses Chinese natural-language values for user-facing fields such as "name" and "description" with no indication that the skill is region-specific or that users can choose a language. Under the policy, forcing a specific language without opt-in can be a natural-language policy violation.
- Content
Natural-Language Policy Violations
Low
- Category
- Not specified by scanner
- Confidence
- 88% confidence
- Finding
This JSON manifest-like file uses Chinese natural-language values for names and descriptions throughout, with no indication that the user can opt into a language or choose an alternate locale. Under the policy rule for natural-language violations, a skill artifact that implicitly forces a specific language without documented choice can be flagged unless the locale restriction is clearly justified.
- Content
Natural-Language Policy Violations
Low
- Category
- Not specified by scanner
- Confidence
- 83% confidence
- Finding
The natural-language fields in this file are entirely in Chinese, and there is no indication that users can choose another language or that the locale restriction is intentionally limited to a Chinese-only context. That can constitute a language policy violation under the stated rule when no opt-in or justification is present.
- Content
Static analysis
No suspicious patterns detected.