T09 · Insecure Skill Coding Practices
- Location
research_logger.sh:90- Finding
Arbitrary sed Program Injection Through Unescaped Template Values
- Content
View full analysis
- Remediation
View remediation
Security audit
Security checks for vulnerabilities and agentic risk
This skill does what it says, but its shell script unsafely mixes user and web-fetched text into sed commands, creating a credible local command-execution risk.
Review this skill before installing. It is purpose-aligned, but do not use it with confidential topics or untrusted research targets unless the template fill is fixed to treat all replacement values as literal data instead of sed syntax, ideally with a safer templating implementation and a preview or no-save mode.
research_logger.sh:90Arbitrary sed Program Injection Through Unescaped Template Values
The script sends the user-supplied topic directly to external helpers (web_search, web_fetch, and gifgrep) without any notice, consent, or sensitivity check. This can leak confidential research subjects, internal project names, or personal data to third-party services, and the skill’s purpose explicitly encourages such transmission, making the privacy risk real rather than hypothetical.
The skill advertises research, GIF matching, and note creation, but does not clearly warn users that fetched web content and generated notes will be automatically persisted into Bear. This can cause users to unknowingly save untrusted, sensitive, or irrelevant content into a long-lived notes store, increasing the risk of privacy leakage, accidental retention, and downstream trust in AI-generated notes.
The script creates a Bear note and, on failure, writes a markdown file locally without clearly informing the user in advance that their query, fetched content, and generated notes will be persisted. While this is consistent with the tool’s stated purpose, it still creates an undisclosed data-retention risk if the topic or collected content is sensitive.