code-understanding
Provides adversarial code comprehension for security research, mapping architecture, tracing data flows, and hunting vulnerability variants to build ground-truth understanding before or alongside static analysis.
55
61%
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 ./.claude/skills/code-understanding/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 content documents a permission auto-approval rule that auto-runs any libexec/raptor-* command when invoked in the exact shown form, effectively enabling privileged/automatic execution of scripts (a potential backdoor/remote execution vector) and the docs repeatedly instruct running those exact libexec/raptor-* commands.
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 skill mandates quoting exact source lines as proof for every assertion and running libexec scripts exactly as shown, which can force the model to reproduce any secret literals present in the code or scripts verbatim in its output.
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 skill explicitly instructs the agent to "Run libexec/ scripts exactly as shown" and notes the permission system "auto-approves" certain commands (SKILL.md:54-55), and also advises executing target binaries for runtime probes (SKILL.md:115-125), which encourages executing code on the host and bypassing normal safeguards.
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
Outsider-authored free text can only enter the LLM via the operator-supplied hunt/teach/trace inputs (e.g., `--hunt` pattern description or `--trace` entry selection), not from any external queue/feed/web source as part of the required runtime workflow.
- Repository
- gadievron/raptor
- Commit
75f6956
- 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.