soia-pkm-clip-web
Pass
Audited by Gen Agent Trust Hub on Jul 16, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill's primary function involves fetching and processing content from external URLs provided by the user. Additionally, the provided installation instructions utilize
npxto download the skill from the author's public repository. - [COMMAND_EXECUTION]: The instructions in
references/obsidian-pdf-export.mddirect the agent to useosascript(AppleScript) on macOS for UI automation to trigger Obsidian's native PDF export feature. It also specifies the use of CLI tools likepdfinfo,pdftoppm, andpdftotextto validate the integrity and content of the generated PDF files. - [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection (Category 8) because it ingests and processes untrusted data from external websites.
- Ingestion points: Web content extracted from user-supplied URLs as described in
SKILL.md. - Boundary markers: Absent. The skill does not instruct the agent to use delimiters or ignore instructions embedded within the scraped content.
- Capability inventory: The agent can write files to the local Obsidian vault and execute system commands (
osascript,pdfinfo, etc.). - Sanitization: No sanitization or filtering logic is mentioned to mitigate the risk of malicious instructions being included in the scraped web data.
Audit Metadata