Skills/PyPI/agent-prompt-injection-firewall-mcp

agent-prompt-injection-firewall-mcp@1.0.13

VERIFIED

Publisher claims: "The WAF for agents. Pattern-based + heuristic firewall scans prompts, RAG documents, tool arguments, A2A payloads for OWASP LLM01 prompt injection BEFORE they reach a downstream agent. Curated from OWASP + academia + production incidents." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry PyPI (MCP server)Publisher csoai-org · joined 1 days agoInstalls 348Last detonated 2 h ago
$claude mcp add agent-prompt-injection-firewall-mcp -- uvx agent-prompt-injection-firewall-mcp
WatchReport an issue

Is [email protected] safe to install?

KillerSkills ran it in the KillerSkills honeypot sandbox (2 scenarios) on 2026-10-26 and scored it 87/100 (Verified). It did what it claims and nothing else we could detect: no undeclared network egress, no credential reads, no persistent instruction writes. Summary: no network, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 0 s · 2 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
0.2sprocessdependency install exit 1
0.3sprocessexec /usr/bin/timeout
0.3sprocessexec .venv/bin/agent-prompt-injection-firewall-mcp
0.3sprocessexited 127: timeout: failed to run command '.venv/bin/agent-prompt-injection-firewall-mcp': No such file or directory
0.3sclaimedno tools/list reply (exit 127)
0.3sprocessscript backend runs setup only

Static findings

MEDIUM
npx invocation of non-well-known packageglama.json:34 · npx invocation of non-well-known package — may execute untrusted codeFix: Pin versions and sources; vendor anything fetched at install time.
AST06

No other findings across 2,309 lines in 39 files.