Security audit
Security checks for vulnerabilities and agentic risk
This skill does exactly what it claims: delete a PDF API Hub cloud file by URL using the user's API key.
Install only if you intend to let the agent delete PDF API Hub files. Before each use, verify the exact URL and API key context, because the skill does not include an explicit confirmation step or recovery guidance.
The skill enables a destructive delete action but does not clearly warn that deletion may be irreversible or cause permanent data loss. In an agent setting, missing safety language increases the chance of accidental destructive use, especially if a user or upstream workflow passes the wrong URL.
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
curl -X POST https://pdfapihub.com/api/v1/file/delete \
-H "CLIENT-API-KEY: your_api_key" \
-H "Content-Type: application/json" \
-d '{ "url": "https://bucket.s3.amazonaws.com/pdf/abc123_my_report.pdf" }'
This JSON manifest/example shows a file deletion request and successful deleted response, but provides no surrounding specificity about when this action should be invoked or any limiting conditions. In a manifest-style file, presenting destructive behavior without explicit scope or exclusions can contribute to overly broad or ambiguous activation semantics.
The manifest exposes a destructive delete capability but provides no built-in warning, confirmation requirement, or usage guidance indicating that deletion is irreversible or should require explicit user intent. In an agent setting, this increases the risk of accidental or socially engineered file deletion, especially because the action is simple, high-impact, and triggered solely by a supplied URL.
The response example uses fixed English status fields such as "success" and "deleted", but these are API field names rather than natural-language instructions to users. Because this is primarily structural configuration rather than a user-facing language mandate, evidence of a policy violation is weak.
No suspicious patterns detected.