Announcing Beacon: Self-improving memory for coding agents
← All skills
Skill

mcp

skill:primeintellect-ai/prime-agent#mcp

Use external MCP services generically from Python - search the supported-service catalog, inspect the user's connections, discover live tool schemas, and call tools on any connection (Notion, Linear, Slack, and the rest of the catalog) without per-service packages.

Verdict
Inconclusive

The analysis could not cover enough of the artifact to decide.

Analyzed Oct 27, 2026, 23:09 UTC at c13415b

Dispute security verdict

If you believe this verdict is incorrect, submit a dispute and we'll review it.

0
findings
—
highest severity
0
threat classes
1,605
files scanned
17/17
checks satisfied
0
package advisories

Why this verdict

  • inconclusive: gap request_unanswered
  • inconclusive: gap skill_frontmatter_invalid at skills/factory/SKILL.md
  • inconclusive: unresolved question on EXFIL

Security findings 0

No individual findings recorded

The inconclusive verdict rests on the open questions and coverage gaps below; 1 candidate finding was refuted on review.

Open questions 2

What the analysis could not settle from the code alone.

[invalid file request] Does this MCP helper implementation read credentials or local files, send workspace/secret data to any endpoint beyond the user's own MCP connections, fetch and execute code from a URL, or write to agent/host config for persistence?
Data exfiltration
[file request skills/mcp/mcp.py] The fenced examples invoke an unshown helper module (mcp.list_plugins, mcp.list_connections, mcp.search_tools, mcp.describe_tool, mcp.call_tool). Does its implementation read credentials or local files, send workspace/secret data to any endpoint beyond the user's own MCP connections, fetch and execute code from a URL, or write to agent/host config for persistence?
Data exfiltration
Refuted findings 1

Candidates the review stage examined and rejected, kept for transparency.

Code execution

criticalRefutedmedium confidence

skills/mcp/SKILL.md instructs the agent to execute Python through an mcp helper module (call_tool, list_connections, search_tools, describe_tool) whose implementation is not part of the consumable artifact content, so the runtime behavior of those calls cannot be reviewed.

result = await mcp.call_tool(
Why it was refuted

The instructed calls are the skill's declared core capability: the artifact openly states that every external service is reached through the same pre-imported (host-provided) mcp module, and the target declares calling tools on any connection as the skill's purpose, so executing through this module is the accepted declared-core-capability carve-out. That the module's implementation lives outside the artifact is a declared host dependency (out of scope), not concealed or undeclared behavior; the skill also documents its error, permission, and credential boundaries.

Coverage gaps 5

Parts of the artifact the static analysis could not fully examine.

context:unanalyzable_binary binary content is only byte-scanned
crates/pa-core/src/auth/manager.rs
context:unanalyzable_binary binary content is only byte-scanned
scripts/release/native-compat/photon_rs_bg.wasm
skill_frontmatter_invalid missing name/description frontmatter
skills/factory/SKILL.md
context:frontmatter_unparseable mapping values are not allowed here
skills/factory/SKILL.md
request_unanswered request.0: invalid file request (evidence_ids not shown in the asking request)