timeline-markdown-notes
Pass
Audited by Gen Agent Trust Hub on Sep 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and parse content from external files in the
input/notes/directory. This creates a vulnerability surface where an attacker could place malicious instructions inside notes to manipulate how the agent extracts, formats, or filters the timeline data. - Ingestion points: Markdown (
.md) and text (.txt) files stored in theinput/notes/directory. - Boundary markers: The skill lacks explicit instructions for the agent to use delimiters or to disregard embedded commands within the input files.
- Capability inventory: The skill writes processed data to the file system at
output/md_notes_entries.json. - Sanitization: There are no defined procedures for sanitizing or validating the contents of the notes before they are processed by the agent.
- [NO_CODE]: The skill does not provide any executable code, scripts, or binaries. It relies entirely on natural language instructions within
SKILL.mdto direct the agent's existing capabilities.
Audit Metadata