initializing-memory
Comprehensive guide for initializing or reorganizing agent memory. Load this skill when running /init, when the user asks you to set up your memory, or when you need guidance on creating effective memory files.
56
65%
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 ./src/skills/builtin/initializing-memory/SKILL.mdSecurity
3 findings: 1 critical severity, 1 high severity, 1 medium severity. 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
The document contains explicit instructions to discover and export local historical session stores, run background subagents with elevated permissions, and automatically commit/push extracted data (including forging commit authors and manipulating credential helpers), which can be abused to collect and exfiltrate sensitive data or establish persistent, hard-to-audit changes.
W007: Insecure credential handling detected in skill instructions.
What this means
The skill handles credentials insecurely by requiring the agent to include secret values verbatim in its generated output. This exposes credentials in the agent’s context and conversation history, creating a risk of data exfiltration.
Why it was flagged
The prompt instructs history-analyzer workers to ingest complete past sessions and "preserve specificity" including exact quotes and details when writing memory files, which would cause the agent to read and potentially output any secrets (API keys, tokens, passwords) verbatim if they appear in those transcripts.
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
The prompt explicitly instructs using a subagent with a "bypassPermissions" capability and to discover/export "every native session store on this machine" and modify projected filesystem memory, which encourages bypassing permissions and accessing/modifying machine-local data beyond normal project files.
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
Step 5b/5a runs `letta trajectories export` and then launches `history-analyzer` workers that read normalized session transcripts from `/tmp/letta-trajectories/<source>/*.json` and include them in subagent prompts (code comments in the workflow indicate the transcript content becomes LLM-readable), which can include outsider-authored text from public/third-party agent harnesses’ persisted histories.
- Repository
- letta-ai/letta-code
- Commit
051b47f
- 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.