cekura-self-improving-agent
Use to close the loop on agent quality — turn a failure signal into a verified fix. Triggers: "improve my agent", "self-improving agent", "auto-tune / iterate on my prompt", "fix my agent from test results", "optimize my prompt based on failures", "rewrite my prompt". ALSO for production-call bug fixing: "fix this prod call issue", "debug and fix call ID", "reproduce this production bug", "regression test before a PR", "fix the bug from this call and open a PR". Works across VAPI, ElevenLabs, and self-hosted agents, and across three fix surfaces — prompt, tool config, and (self-hosted) owned source code, including infra-flavored / forked-SDK bugs, which are reproduced and validated on Cekura (never a code test) and, for source edits, shipped as a PR.
74
—
Does it follow best practices?
Impact
—
No eval scenarios have been run
Advisory
Suggest reviewing before use
Security
2 findings — 2 medium severity. This skill can be installed but you should review these findings before use.
W011: Third-party content exposure detected (indirect prompt injection risk)
What this means
The skill exposes the agent to untrusted, user-generated content from public third-party sources, creating a risk of indirect prompt injection. This includes browsing arbitrary URLs, reading social media posts or forum comments, and analyzing content from unknown websites.
Why it was flagged
Third-party content exposure detected (high risk: 0.85). Outsider-authored free text is ingested via the “prod call inputs route through Collect → Debug → Reproduce” path: COLLECT.2 fetches production call logs/transcripts (including flattened transcript text) from `result_id`/`run_ids`/`call_ids`, and that transcript text is then used to build the harness and is re-read into the LLM context during Debug/Fix/Overfitting-Gate.
W013: Attempt to modify system services in skill instructions
What this means
The skill prompts the agent to compromise the security or integrity of the user’s machine by modifying system-level services or configurations, such as obtaining elevated privileges, altering startup scripts, or changing system-wide settings.
Why it was flagged
Attempt to modify system services in skill instructions detected (high risk: 0.70). The skill explicitly allows editing self-hosted source and running a user-provided "redeploy_command" (a shell command) to apply changes — a capability that can modify machine state or execute privileged operations even though the text warns about privileged redeploys.
- Repository
- cekura-ai/cekura-skills
- Commit
f0854af
- Audited
- Security analysis
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.