T09 · Insecure Skill Coding Practices
- Location
knowledge/domain.md:15- Finding
Academic Search Requests Use an Unencrypted arXiv API Endpoint
- Content
View full analysis
- Remediation
View remediation
Security audit
Security checks for vulnerabilities and agentic risk
This academic-search skill is mostly purpose-aligned, but its very broad triggers and plaintext arXiv endpoint create avoidable review-worthy risk.
Review the trigger list before installing, especially if your agent auto-activates skills from fuzzy matches. Use the skill only for intentional scholarly literature searches, avoid putting confidential research topics into broad prompts, and prefer an updated version that uses HTTPS-only arXiv endpoints and narrower academic-specific triggers.
knowledge/domain.md:15Academic Search Requests Use an Unencrypted arXiv API Endpoint
The trigger phrase "find papers" begins with a built-in command verb and can shadow or conflict with generic "find" behavior in systems that use prefix or fuzzy trigger matching. This creates command-routing ambiguity that may let this skill intercept requests unexpectedly, especially when a user intends a general search rather than explicit academic workflow execution.
The trigger list includes highly generic terms such as "research" that are common in normal conversation and can cause the skill to activate outside a clearly academic-search context. Overbroad activation increases the chance of unintended tool use, response hijacking, or routing a user into this skill when another skill or default behavior would be more appropriate.
Triggers like "cite" and "citation" are broad and overlap with many ordinary requests, including non-academic formatting or general writing assistance. This can lead to accidental invocation of the skill and unintended dependence on its external-search workflow, which widens attack surface and may disrupt correct command routing.
The activation rule fires on broad concepts like paper search, literature review, or research discovery without defining exclusions or minimum specificity. Because those intents frequently appear in mixed-purpose user requests, the skill may activate too aggressively, causing unintended external searches and overshadowing more suitable skills or built-in behaviors.
Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.
- **Fix**: Only return papers actually retrieved from database API responses. If the search returns fewer than 5 relevant results, report that honestly rather than padding with fabricated entries. Include the database query used so the user can verify.
### 15. Ignoring Open Access Status
- **Problem**: Returning papers behind paywalls without checking for open-access alternatives. Users without institutional access cannot read the papers.
- **Fix**: For each paper, check: (a) arXiv preprint version, (b) Semantic Scholar `openAccessPdf` field, (c) author's personal website or institutional repository. Flag papers with no open-access version available and suggest the user check their institutional library access.
## Workflow Anti-Patterns
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
### API Endpoints
#### Paper Search
- **URL**: `GET https://api.semanticscholar.org/graph/v1/paper/search`
- **Rate Limit**: 100 requests/5 minutes (unauthenticated); 1 request/second with API key
| Parameter | Description | Example |
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
### API Endpoints
#### Paper Search
- **URL**: `GET https://api.semanticscholar.org/graph/v1/paper/search`
- **Rate Limit**: 100 requests/5 minutes (unauthenticated); 1 request/second with API key
| Parameter | Description | Example |
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
### API Endpoints
#### Paper Search
- **URL**: `GET https://api.semanticscholar.org/graph/v1/paper/search`
- **Rate Limit**: 100 requests/5 minutes (unauthenticated); 1 request/second with API key
| Parameter | Description | Example |
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
### API Endpoints
#### Paper Search
- **URL**: `GET https://api.semanticscholar.org/graph/v1/paper/search`
- **Rate Limit**: 100 requests/5 minutes (unauthenticated); 1 request/second with API key
| Parameter | Description | Example |
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
### API Endpoints
#### Paper Search
- **URL**: `GET https://api.semanticscholar.org/graph/v1/paper/search`
- **Rate Limit**: 100 requests/5 minutes (unauthenticated); 1 request/second with API key
| Parameter | Description | Example |
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
### API Endpoints
#### Paper Search
- **URL**: `GET https://api.semanticscholar.org/graph/v1/paper/search`
- **Rate Limit**: 100 requests/5 minutes (unauthenticated); 1 request/second with API key
| Parameter | Description | Example |
The trigger list contains very broad terms such as "research," "scholar," "cite," and "citation," which are likely to match many unrelated user requests and cause the skill to activate unexpectedly. In an agent environment, overbroad activation can route prompts into external search and synthesis behavior when the user did not intend it, increasing the chance of unnecessary data exposure, confusing tool use, or prompt-scope expansion.