T09 · Insecure Skill Coding Practices
- Location
assets/trinity-compress.config.json:6- Finding
Context-Insensitive Rewriting Can Weaken Security-Sensitive Agent Instructions
- Content
View full analysis
- Remediation
View remediation
Security audit
Security checks for vulnerabilities and agentic risk
This skill appears to be a local prompt-compression tool, but its default rules can broadly rewrite agent instruction files in ways that may change their meaning.
Review this carefully before installing. It does not show evidence of exfiltration or hidden execution, but its defaults are risky for system prompts and skill files. Only use it on version-controlled files, inspect the full diff before running an agent with compressed prompts, and avoid applying it to safety, credential, authorization, or tool-permission instructions unless you have manually verified that meaning is preserved.
assets/trinity-compress.config.json:6Context-Insensitive Rewriting Can Weaken Security-Sensitive Agent Instructions
This configuration targets prompt and skill files, then removes entire phrases such as cautionary or emphasis-oriented language without any protected-term list or safety-aware exclusions. In prompt-governing files, broad phrase deletion can silently strip warnings, constraints, or risk qualifiers and thereby weaken downstream safety behavior or change instruction meaning.
The instruction-compression rules rewrite normative prompt language globally across system and skill prompt targets, including transformations around obligations and prohibitions such as replacing or deleting phrases like 'You should', 'You need to', and contractions of 'do not'. Because these files define agent behavior, overly broad rewriting can materially alter force, scope, or clarity of security instructions and create prompt-meaning drift that weakens safeguards.