T08 · Insecure Dependencies
- Location
clawhub.json:4- Finding
Unpinned Trading SDK Creates a Supply-Chain Risk
- Content
View full analysis
- Remediation
View remediation
Security audit
Security checks for vulnerabilities and agentic risk
The skill is mostly coherent and disclosed, but it includes real-money trading capability driven by fragile web-search data and trading credentials without strong live-run controls.
Review before installing. Keep DRY_RUN enabled unless you have audited the strategy, use dedicated low-limit Simmer and Tavily keys, run it in an isolated environment, pin dependencies, and avoid scheduling live mode until cumulative spend and position limits plus explicit confirmation are added.
clawhub.json:4Unpinned Trading SDK Creates a Supply-Chain Risk
scripts/signal.py:24External Search Requests Lack Timeout, Error Handling, and Response Validation
Credentials or environment variables flow to a network sink. This is a high-confidence indicator of credential exfiltration.
return players
def tavily_search(query):
r = requests.post("https://api.tavily.com/search", json={"api_key": TAVILY_API_KEY, "query": query, "max_results": 3, "include_domains": ["fbref.com", "espn.com", "whoscored.com"]})
results = r.json().get("results", [])
return " ".join([x.get("content", "") for x in results])
The skill description says it 'prints buy signals', but the code contains a live trading path that executes client.trade(...) whenever DRY_RUN is changed. This creates a dangerous capability mismatch: a reviewer or operator may approve or run the skill believing it is signal-only, while it can place real trades with authenticated account access.
The skill documentation indicates it uses environment variables and network access, but it does not declare an explicit tool scope such as permissions or allowed-tools. That creates unnecessary ambiguity about what the agent is permitted to access, increasing the risk of over-privileged execution, unintended secret exposure, or broader network activity than reviewers expect.
A general web search API provides broader external access than is necessary for a narrowly scoped task of reading football assist statistics for valuation. Even without direct evidence of abuse in this file, this overbroad capability can enable unintended data retrieval paths, reduce auditability, and violate least-privilege expectations for the skill.
The manifest requests a Tavily API key and explicitly states it may fetch stats from FBref, ESPN, and WhoScored, while the skill description says the valuation is FBref-based. This mismatch broadens the data-access scope beyond what the user would reasonably expect, increasing the risk of unnecessary third-party data access and making the skill's behavior less transparent.
The notes discuss future live trading and API execution without any accompanying warning about financial risk, real-money loss, or the need for explicit user authorization. In a financial/trading context, normalizing automated execution without risk disclosures can lead users to deploy unsafe automation and suffer monetary harm, especially given the notes also acknowledge unreliable data quality and placeholder calibration.
The heading labels 'Portugal (Lamine Yamal)', but the player annotation does not match the national-team context presented by the heading. This is an active documentation contradiction within the file, which can mislead downstream users or agents about which player/team the schedule refers to.
The script initializes an authenticated SimmerClient from environment credentials even though the stated purpose is only to print signals. Loading trading-capable credentials unnecessarily increases blast radius: any later code path, accidental modification, or imported behavior can use those credentials to act on the account.
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
return players
def tavily_search(query):
r = requests.post("https://api.tavily.com/search", json={"api_key": TAVILY_API_KEY, "query": query, "max_results": 3, "include_domains": ["fbref.com", "espn.com", "whoscored.com"]})
results = r.json().get("results", [])
return " ".join([x.get("content", "") for x in results])
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
return players
def tavily_search(query):
r = requests.post("https://api.tavily.com/search", json={"api_key": TAVILY_API_KEY, "query": query, "max_results": 3, "include_domains": ["fbref.com", "espn.com", "whoscored.com"]})
results = r.json().get("results", [])
return " ".join([x.get("content", "") for x in results])
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
return players
def tavily_search(query):
r = requests.post("https://api.tavily.com/search", json={"api_key": TAVILY_API_KEY, "query": query, "max_results": 3, "include_domains": ["fbref.com", "espn.com", "whoscored.com"]})
results = r.json().get("results", [])
return " ".join([x.get("content", "") for x in results])
The code sends TAVILY_API_KEY in the JSON body of a network request to an external service. Although the script prints general dry-run and trading messages, there is no warning, comment, or docstring disclosing that a credential will be used and transmitted to a third-party API.
The manifest says the skill compares Simmer market prices to an FBref-based form value, implying a relatively specific source and methodology. These notes instead document collecting both player stats and prices through generic web searches and snippet extraction, which is materially broader and different from the stated FBref-based approach.
The documented purpose is limited to scanning markets, comparing values, and printing buy signals. The recommendation to use Simmer API 'for price data and trading' introduces an active trading capability that goes beyond the stated intent and creates tension with the declared read/analysis-oriented behavior.
The manifest describes a skill that scans Simmer markets and compares prices to FBref-based form values, but this file is a manually extracted tournament schedule from The Guardian with target-player notes. While reference data can support analysis, the file's content is not clearly tied to 'Most Assists' market valuation and broadens the apparent behavior toward fixture/path tracking.