bib-manage
Warn
Audited by Gen Agent Trust Hub on Oct 5, 2026
Risk Level: MEDIUMDYNAMIC_CONTEXT_INJECTIONDYNAMIC_EXECUTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [DYNAMIC_CONTEXT_INJECTION]: The
SKILL.mdfile includes a shell command within the dynamic context syntax (!...) that executes at skill load time. This command attempts to locate and runskill-tocto generate a table of contents for the skill's reference materials. - [DYNAMIC_EXECUTION]: The
scripts/bibman.pyscript dynamically loads a local dependency,pincite.py, usingimportlib.util.spec_from_file_location. This allows the skill to execute code from a sibling project at runtime. - [COMMAND_EXECUTION]: The skill uses
subprocess.runto execute the localpaperpileCLI tool, passing user-derived search queries to retrieve bibliographic data in JSON format. - [EXTERNAL_DOWNLOADS]: The skill makes network requests to
api.crossref.organdwww.govinfo.govto retrieve bibliographic metadata and Federal Register PDF documents. - [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted bibliographic data and PDF filenames which are interpolated into search queries and metadata fields.
- Ingestion points: Bibliographic entries in
.bibfiles and filenames within the project's PDF directory. - Boundary markers: None are present to distinguish between trusted instructions and external data in the processed fields.
- Capability inventory: The skill possesses network access (urllib), shell execution capabilities (subprocess), and the ability to overwrite local bibliography files.
- Sanitization: The script uses regular expressions and similarity matching to validate data, but does not perform comprehensive sanitization or escaping of the metadata before using it in API queries.
- Ingestion points: Bibliographic entries in
Audit Metadata