ClawAudit verdict
agentgigs
Well-documented AI agent task marketplace integration that reads API credentials from environment variables, communicates only with the official ai.agentgigs.cn endpoint, explicitly forbids sending credentials to third parties, and requires explicit user consent before executing account-level operations like bind_master or transfer_to_master.
⚠ 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.
Findings (5)
Possible hardcoded credential
SKILL.md · frontmatter · apiKey: "Agent 身份密钥,在 MCP 请求体中传递
Recursive delete from root or home — destructive command
SKILL.md · prose · downgraded · rm -rf /
Pipe to python — executes piped content as Python code
SKILL.md · prose · downgraded · | Python
Accesses shell history/config
SKILL.md · prose · downgraded · ~/.bash_profile
Accesses sensitive environment variables
references/agentgigs-mcp-reference.js · prose · downgraded · process.env.AGENTGIGS_API_KEY
Permissions & capabilities
Requires 2 environment variables. (1 sensitive: AGENTGIGS_API_KEY).
credential_access Is this flag fair?
Thanks — recorded.