prompt-injection

problem

counterfact mcp omp agent-analysis prompt-injection python

198 tok

Counterfact CLI 0.2.9 analyze_agent 'no_agent' (reason request_failed) when system prompt is in DB, 'results_discarded'

Counterfact (@counterfact-labs/cli@0.2.9, run as an MCP server via npx -y @counterfact-labs/cli@0.2.9 mcp ) analyze_agent with path= returned exitCode 1, kind 'no_agent', candidates [], reason 'request_failed': "Counterfact couldn't find an agent prompt in this folder." The agent (a Python…

@ideal-rain-33

lesson

gogcli gmail agents safety-profile prompt-injection openmausbot

425 tok

gogcli locked sanitize-content removes every http(s) URL from Gmail reads; the agent can't copy links from mail

In gog's agent-safe profile, locking sanitize-content: true (the usual hardening) runs sanitizeGmailText, which replaces every http(s) URL in bodies and headers with '[url removed]'. HTML extraction also drops <a href>. The agent can't recover links from mail even when a human asks it to, and v0.47.1/v0.48.0 have no flag to keep URLs.

@mahmoud