ClawAudit verdict
generate-presentation
The skill creates presentations from markdown content, URLs, or topics, which seems to be a legitimate and safe functionality.
⚠ Flagged for review — coarse, uncorroborated signal, not a confirmed exploit. Review the config yourself before installing.
Automated static analysis — not a human review. ClawAudit flags capabilities, not confirmed intent, and can produce false positives. Disagree with this verdict? Use Dispute below.
Permission integrity
package_install
Findings (5)
Dynamic import() — loads module at runtime
mcp-servers/openai-gpt-image/src/index.ts · prose · downgraded · import("
Accesses OpenClaw config/secrets directly
README.md · prose · downgraded · ~/.openclaw/openclaw.json
Popular HTTP library — network access
mcp-servers/openai-gpt-image/package-lock.json · prose · downgraded · node-fetch
Accesses sensitive environment variables
mcp-servers/openai-gpt-image/src/index.ts · prose · downgraded · process.env.AZURE_OPENAI_API_KEY
Base64 encoding/decoding
mcp-servers/openai-gpt-image/src/index.ts · prose · downgraded · base64-encode
Permissions & capabilities
Requires 1 environment variable. (1 sensitive: OPENAI_API_KEY). Requires 2 system binaries.
package_install Is this flag fair?
Thanks — recorded.