T08 · Insecure Dependencies
Warning
- Location
SKILL.md:7- Finding
Unpinned Third-Party Dependencies Create a Supply-Chain Risk
- Content
View full analysis
- Remediation
View remediation
Security audit
Data Analyzer
Security checks for vulnerabilities and agentic risk
Overview
This is a local file-analysis helper with some overbroad feature claims and unpinned Python dependencies, but I found no hidden upload, persistence, privilege escalation, or destructive behavior.
Install only in a virtual environment you trust, preferably with pinned dependency versions. Use the skill on explicit folders or files, since it recursively reads supported local documents and may include extracted text or table contents in its analysis results. Do not rely on the advertised chart/report/merge features unless they are implemented in a later version.
Vulnerability Patterns
- Insecure DependenciesIntroduces malicious components through unsafe dependency sources
- 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
Findings (1)
Vulnerability Patterns
- Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
- 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
Findings (6)
Description-Behavior Mismatch
Medium
- Category
- Not specified by scanner
- Confidence
- 96% confidence
- Finding
The manifest says the skill supports report generation in Markdown/Excel/Word/PDF and lists chart visualization as a feature. However, the implementation only scans folders, parses supported files, and builds a Python summary object; there is no code that generates reports, writes output files, or creates charts.
- Content
Description-Behavior Mismatch
Medium
- Category
- Not specified by scanner
- Confidence
- 94% confidence
- Finding
The description and trigger examples present this skill as able to aggregate data, compute statistics such as sums/averages/trends, and compare multiple files. The actual code only counts rows/columns, extracts text, and packages per-file results; it does not merge datasets, calculate statistics beyond simple counts, or compare files.
- Content
Vague Triggers
Medium
- Category
- Not specified by scanner
- Confidence
- 87% confidence
- Finding
Ambiguous trigger conditions weaken invocation boundaries and increase the chance that the skill is selected in contexts where it should not run. Because this skill recursively scans folders and reads multiple local file types, accidental over-selection can expand data exposure and process more user content than necessary.
- Content
Vague Triggers
Medium
- Category
- Not specified by scanner
- Confidence
- 93% confidence
- Finding
The trigger phrase "Summarize the data" is broad enough to activate on many ordinary user requests outside the intended file-analysis scope. That can cause the agent to invoke this skill on unintended inputs, leading to unnecessary file scanning or handling of local documents the user did not specifically intend to process.
- Content
Scope Creep
Low
- Category
- Excessive Agency
- Confidence
- 70% confidence
- Finding
Skill's behavior or capabilities extend beyond its stated purpose. Scope creep allows an agent to perform actions unrelated to its documented functionality, increasing the attack surface.
- Content
text permit persons to whom the Software is furnished to do so. THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
Natural-Language Policy Violations
Low
- Category
- Not specified by scanner
- Confidence
- 76% confidence
- Finding
The file advertises multi-language capability, but the usage section shows agent responses forced into Chinese even when the user prompt is in English. This may violate language/locale policy expectations when no opt-in or preference-selection behavior is documented.
- Content
Static analysis
No suspicious patterns detected.