source-to-skill
Pass
Audited by Gen Agent Trust Hub on Nov 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted external documents (books, articles, transcripts) to generate behavior-shaping instructions for other agents. This creates a surface where malicious instructions embedded in source material could influence agent behavior.
- Ingestion points: Local files, directories, and URLs are processed via the
scripts/extract.pyhelper script and standard agent file tools, as described in theSKILL.mdworkflow. - Boundary markers: The skill includes a
Source integrity gatethat explicitly instructs the agent to treat source content as data rather than instructions and to ignore any embedded overrides or safety bypass attempts. - Capability inventory: The skill is authorized to write files to the
.agents/skills/directory and execute shell commands via its Python helper script. - Sanitization: The
Path privacy gateandProvenancesections inSKILL.mdmandate the redaction of local absolute paths and temporary directory information from any generated artifacts to prevent sensitive path exposure. - [COMMAND_EXECUTION]: The provided Python helper script (
scripts/extract.py) uses thesubprocessmodule to call system binaries for file conversion tasks. - Evidence: The script invokes
pdftotextfor PDF extraction andebook-convert(from Calibre) for specialized e-book formats. - Safety Measures: The script implements internal safety limits for archive processing (e.g.,
MAX_ARCHIVE_MEMBERS,MAX_ARCHIVE_TOTAL_BYTES) to mitigate risks from malicious archives such as zip bombs.
Audit Metadata