ce-compound
Document a recently solved problem as a durable repo learning, or capture project vocabulary in CONCEPTS.md. Use when capturing a learning after work.
63
76%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
View guide
Critical
Do not install without reviewing
Fix and improve this skill with Tessl
tessl review fix ./skills/ce-compound/SKILL.mdSecurity
1 critical severity finding. Installing this skill is not recommended: please review these findings carefully if you do intend to do so.
E006: Malicious code pattern detected in skill scripts.
What this means
Detected high-risk code patterns in the skill content — including its prompts, tool definitions, and resources — such as data exfiltration, backdoors, remote code execution, credential theft, system compromise, supply chain attacks, and obfuscation techniques.
Why it was flagged
This skill bundle intentionally discovers and reads local agent session files (user home session stores), extracts user/assistant text and tool inputs (paths, commands, prompts), and instructs embedding those contents into subagent prompts/artifacts — a deliberate data-collection flow that creates a high risk of sensitive-data exposure or exfiltration if forwarded outside the host.
Low
Low-risk findings.
1 low severity finding. Worth noting, but not necessarily harmful.
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
High likelihood: in Full mode the orchestrator runs the bundled `scripts/session-history/` extraction pipeline, which reads pre-existing outsider-authored conversational text from session JSONL files under `~/.claude/projects/`, `~/.codex/sessions/`, `~/.cursor/projects/`, and `~/.pi/agent/sessions/`, then passes the extracted prose/summaries into the session-historian synthesis subagent prompt and into the LLM context.
- Repository
- EveryInc/compound-engineering-plugin
- Commit
a9f6d53
- 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.