robotframework-libdoc-explain
Warn
Audited by Gen Agent Trust Hub on Feb 21, 2026
Risk Level: MEDIUMCOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION] (MEDIUM): Relative path traversal detected in script file. \n
- Evidence: The file
scripts/rf_libdoc.pycontains a relative path../../robotframework-libdoc-search/scripts/rf_libdoc.py. \n - Risk: Referencing files in parent directories (
../../) is a security anti-pattern that attempts to break out of the skill's local directory. If the agent environment follows this path, it could lead to the execution of code not contained within the audited skill package, potentially hijacking local files or executing unauthorized logic. \n- [DATA_EXPOSURE] (LOW): Indirect Prompt Injection Surface (Category 8). \n - Ingestion points: The skill reads library and resource documentation from external Robot Framework files. \n
- Boundary markers: Absent. The prompt instructions in
SKILL.mddo not specify delimiters to separate untrusted documentation content from system instructions. \n - Capability inventory: The skill uses
scripts/rf_libdoc.pyto parse and return structured documentation. \n - Sanitization: Absent in the provided snippets. \n
- Risk: Untrusted documentation strings provided via the
--libraryor--resourceflags could contain malicious instructions designed to manipulate the agent's next steps.
Audit Metadata