daily-papers-notes
Pass
Audited by Gen Agent Trust Hub on Mar 9, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes shell commands to run local Python scripts (
python3 ../_shared/generate_concept_mocs.pyandpython3 ../_shared/generate_paper_mocs.py) for index refreshing. - [COMMAND_EXECUTION]: The skill performs Git automation including
git add,git commit, andgit pushwithin the user's vault path to maintain version history of notes. - [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface by processing external, potentially untrusted data to drive its workflow.
- Ingestion points: Data is read from
/tmp/daily_papers_enriched.jsonand markdown files located in the{DAILY_PAPERS_PATH}directory. - Boundary markers: The skill does not employ explicit boundary markers or 'ignore' instructions to isolate processed content from its logic.
- Capability inventory: The agent has the ability to execute shell commands, perform Git operations, delete files (replacing poor-quality notes), and invoke the
/paper-readerskill. - Sanitization: There is no evidence of sanitization or validation for the 'method_names' or 'paper titles' extracted from files before they are used in file path construction or logic branching.
Audit Metadata